aayudha docs Built from de79988 (2026-10-26)
Menu

Verbs

aayudha has 40 verbs and 19 plumbing commands. This page is generated from the verb registry (internal/verbs/registry.go), the same source as the CLI, the MCP schemas, and each skill's frontmatter.

Verb Accountable seat Summary
grill Product Strategist Interview a human until a work item of the given type is complete and passes validation, then write it as an issue.
slice Product Strategist Split a Feature into XS-L stories with observable criteria, dependencies, and a layer footprint; close XL items as split.
plan Code Architect Plan a story: one checkpoint per layer, contracts, tests, instrumentation, and rollback.
decide Founder Record a Decision with options, evaluation, and recommendation; accept it, supersede it, or file a floor waiver.
counsel Founder Consult the Founder's Sage on any topic, issue, Decision, path, or PR: the call and its door, three readings, one recommendation, cited proof, and the next aayu step; advice only, never a review.
triage Product Strategist Classify intake issues as Feedback, Bug, or Incident by label only; never edits bodies or touches non-intake issues.
brain Product Strategist Keep the product brain: an Obsidian vault on the orphan brain branch; init, checkpoint its generated links, check, or open it.
build AI Native Engineer Build a Ready story or bug in a worktree with checkpoint commits per layer, verify each checkpoint, and open a PR.
verify AI Native Engineer Run the deterministic floors (coverage, SAST, secrets, deps, a11y, perf) and record results in a proof pack.
inspect Engineering Manager Adversarially review a PR against its plan, pack, and criteria; return a structured disposition: merge, fix, or rebuild.
ship Engineering Manager Squash-merge a PR after a green merge gate and a human pass, write the Complete section, and clean up.
release DevOps & DevEx Tinkerer Promote a Release along dev, rolling, main; stamp included stories released and trigger measurement.
proof Quality Architect Push, get, verify, or list proof packs on the ledger branch; comment is the merge gate's pack check.
ready Product Strategist Validate a work item for Ready, label it status:ready, and post the Ready snapshot; --check is read-only.
research UX Researcher & Evolutionist Gather pinned design references (URLs and IDs only) and user research for a Feature.
wireframe UX Researcher & Evolutionist Produce wireframes for a Feature's states from its research and criteria.
mockup UX Researcher & Evolutionist Produce design-system mockups for a Feature from its wireframes.
prototype UX Researcher & Evolutionist Build a flagged, working prototype of a Feature with Code Connect mapping and a Figma screenshot diff.
review UX Researcher & Evolutionist Critique UI with a model lane and a deterministic lane; dispositions recapture, rebuild, fix, or ship.
polish UX Researcher & Evolutionist Apply a review critique to a PR's UI and re-run review.
baseline UX Researcher & Evolutionist Capture visual baselines for a commit SHA.
experiment Revenue Architect Design an experiment for a Feature: hypothesis, metric, flag, and minimum sample size.
readout Revenue Architect Read out an experiment's lift once it reaches minimum sample and write the Result.
respond Production Engineer Respond to an incident: propose an ops catalog action, execute it only through human approval, keep the timeline.
status Engineering Manager Roll up status, health, risk, proof coverage, decisions, and cost per Goal, Initiative, and Feature.
audit Auditor Audit floors, proof coverage, waivers, decision SLAs, autonomy exceptions, and unlogged writes; write a reproducible report.
retro Engineering Manager Compare estimates with observed delivery, corrections, floor misses, and cost; file findings as Feedback issues.
measure Data & AI Architect Measure a Goal or Initiative against its baseline from analytics exports or live cloud pulls and write the Result.
evolve AI Native Engineer Turn accepted retro Feedback into a failing eval case, then a skill diff that passes it, opened as an agent-authored PR.
brief Mentalist Explain work to an audience in a chosen register and purpose as a grounded, accessible HTML brief.
tell Marketer & Documenter Write docs, guides, changelogs, release notes, launch copy, or brand copy that cite only proven Features; publish is human-only.
init Founder Set up a product repo: labels, issue types, forms, config, ledger branch, and optionally projects, gates, identity, integrations.
install DevOps & DevEx Tinkerer Install skill copies, lock.toml, MCP registration, and hooks for each host; shows a diff unless --apply.
doctor DevOps & DevEx Tinkerer Check tools, tokens, identity, config, host installs, and existing CI; --fix re-syncs copies after showing a diff.
chart Data & AI Architect Chart an issue's data or AI design before planning: decisions, metrics, sources, platform, and retention; or evidence, permissions, abstention, and evals.
survey Code Architect Survey a codebase with no product docs: index it, check an evidence-backed analysis and backlog, and capture golden outputs for parity.
investigate Production Engineer Investigate an incident from bounded telemetry queries to the deployed revision and the implicated code, and check the note; it proposes a mitigation, never runs one.
slo Production Engineer Define SLOs and error budgets from the user's side, measure them from a sanitised export, and record the budget that gates release.
runbook Production Engineer Write and check runbooks: confirm a known failure with a bounded query, mitigate it only through the ops catalog, verify it, and roll it back.
scope Product Strategist Plan a release's scope in its version milestone, draft it, have a person baseline it, hand it off, assign Feedback, and hold drift to the change budget.

grill

Interview a human until a work item of the given type is complete and passes validation, then write it as an issue.

Usage: aayu grill <type> [flags]

Field Value
In plain words Interviews you, one question at a time, until an idea is a complete work item, then files it on GitHub.
Journey stage Shape the goal
Accountable seat Product Strategist
Model lane spec
Layers all
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates validator, baseline, halt
Outputs issue, design/brand.yaml, assessment
Built in WP5.3
Skill grill
Input Type Required Description
<type> enum: goal, initiative, feature, story, bug, decision, experiment, release, feedback, incident, brand yes Work-item type (internal/workitems), or brand for design/brand.yaml.
--parent issue no Parent issue to link the new work item under.
--title string no Title of the drafted work item.
--body string no Drafted issue body in the issue-form layout (### sections), or the brand YAML for brand.
--labels string no Comma-separated label-held fields, e.g. effort:S,priority:P2.
--idea string no The request in the human's own words. With --assess, the idea to assess; with a draft, the request its Provenance must quote and resolve.
--assess bool no Read-only fact pass for the idea: the vagueness gate (unpack or pass, with its reasons), its vague qualifiers, abbreviations, and missing outcome with the dimensions to ask about, the product types, and the routes, states, components, tokens, tests, events, related stories, floors, and layers it touches (repository content is reported as untrusted data).
--create bool no Write the validated draft: the issue (through the actions log), or design/brand.yaml; without it grill only validates.

slice

Split a Feature into XS-L stories with observable criteria, dependencies, and a layer footprint; close XL items as split.

Usage: aayu slice <feature> [flags]

Field Value
In plain words Splits a Feature into small stories, each with checkable promises, the parts of the code it touches, and its order.
Journey stage Break it down
Accountable seat Product Strategist
Model lane plan
Layers all
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates validator, halt
Outputs stories, footprint
Built in WP5.4
Skill slice
Input Type Required Description
<feature> issue yes Feature (or XL story) to slice.
--draft path no JSON file with the stories the host's model sliced (evals/schemas/slice.json); without it slice reports the footprint to slice within.
--create bool no Create the validated stories under the Feature (through the actions log) and close an XL story as split; without it slice only validates.

plan

Plan a story: one checkpoint per layer, contracts, tests, instrumentation, and rollback.

Usage: aayu plan <story> [flags]

Field Value
In plain words Plans a story one layer at a time: what changes, how it is tested, and how to roll it back.
Journey stage Break it down
Accountable seat Code Architect
Model lane plan
Layers all
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates validator, halt
Outputs plan, technical-design, footprint, em-review
Built in WP5.4
Skill plan
Input Type Required Description
<story> issue yes Story or bug to plan, or a Feature to write its technical design for.
--draft path no JSON file with the plan the host's model wrote (evals/schemas/plan.json), or a Feature's technical design (contracts, layers, story order, rollback); without it plan reports what to plan.
--create bool no Write the validated plan to the ledger (specs//plan.json) and the story, or a Feature's design (specs//design.json); without it plan only validates.
--approve bool no Record the Engineering Manager's plan-time review of a plan that touches an [autonomy] never layer (human identity only). Human identity only; never exposed over MCP.
--solo-bypass bool no Solo mode only (one human, no bot App): record that a never-layer plan proceeds with no plan-time review, after your story comment starting "Solo-mode bypass:"; a bypass, never an approval. Human identity only; never exposed over MCP.

decide

Record a Decision with options, evaluation, and recommendation; accept it, supersede it, or file a floor waiver.

Usage: aayu decide [<decision>] [flags]

Field Value
In plain words Records a real choice with its options and a recommendation; only a person with the authority accepts it.
Journey stage Break it down
Accountable seat Founder
Model lane spec
Layers all
Writes as human
Who reasons host
Surfaces cli, skill, mcp
Gates decision-authority, human-identity
Outputs decision, waiver, decision-pack
Built in WP5.6
Skill decide
Input Type Required Description
<decision> string no Decision issue; without one, the SLA sweep over every open Decision. With --waiver, the story or bug to waive a floor on. With --pack, any issue, or a question in quotes.
--accept string no Option to accept, by its number or its name (human identity only). Human identity only; never exposed over MCP.
--waiver string no Floor to waive; creates a floor-waiver Decision.
--pack bool no On demand, read-only: the owning seat's twin, its persona at the team stage, the cited facts, and the decision-pack outline (WP5.1b).
--seat string no With --pack: the seat whose twin works the decision instead of the one the topic picks.
--draft string no With --pack: a pack draft (Markdown file) to check for every part and cited claims.

counsel

Consult the Founder's Sage on any topic, issue, Decision, path, or PR: the call and its door, three readings, one recommendation, cited proof, and the next aayu step; advice only, never a review.

Usage: aayu counsel [<topic>] [flags]

Field Value
In plain words Asks the founder's sage for a steer on anything, with the evidence behind it and the next step; it advises and never approves or decides.
Journey stage Explain it
Accountable seat Founder
Model lane spec
Layers all
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates halt
Outputs counsel, grounding
Built in WP5.6d
Skill counsel
Input Type Required Description
<topic> string no A question in quotes, an issue or Decision as #N, or a path in this checkout; or use --pr or --issue.
--pr pr no Pull request to counsel on: its changed files by layer, its proof pack, and its builder family.
--issue issue no Issue or Decision to counsel on: it, its parent, and its links.
--draft path no Markdown counsel the host's model wrote; counsel checks every part, the stage's artefact, and every citation. Without it, counsel prints the grounding and the outline.
--post bool no Post the checked counsel on the PR or issue as one comment labelled counsel, replaced in place on a rerun (through the actions log); needs --draft and --pr or --issue. Never a review or an approval.

triage

Classify intake issues as Feedback, Bug, or Incident by label only; never edits bodies or touches non-intake issues.

Usage: aayu triage [<issue>] [flags]

Field Value
In plain words Sorts incoming reports into feedback, bugs, and incidents by label, without editing what people wrote.
Journey stage Keep it running
Accountable seat Product Strategist
Model lane chore
Layers none
Writes as bot
Who reasons hybrid (the host's model passes --as; never in product CI)
Surfaces cli, skill, mcp
Gates labels-only, halt
Outputs labels
Built in WP2.9
Skill triage
Input Type Required Description
<issue> issue no Intake issue to classify; without it, list the open intake issues and change nothing (the weekly triage loop).
--as enum: feedback, bug, incident no Class chosen by the host's model; without it the binary asks the triage lane's model.

brain

Keep the product brain: an Obsidian vault on the orphan brain branch; init, checkpoint its generated links, check, or open it.

Usage: aayu brain <action> [flags]

Field Value
In plain words Keeps the product's lasting knowledge as linked notes that link to issues and outlive any one person.
Journey stage Explain it
Accountable seat Product Strategist
Model lane chore
Layers none
Writes as bot
Who reasons none
Surfaces cli, skill, mcp
Gates halt
Outputs vault, check-report
Built in v0.3.0
Skill brain
Input Type Required Description
<action> enum: init, checkpoint, check, open yes init: create the brain branch and the vault; checkpoint: refresh the generated blocks from the repository's records and keep every word a person wrote; check: links, frontmatter, sources, STE sentence length, and no pasted Completion Goal line or issue label; open: print how to open the vault in Obsidian.
--workstream string no With init: add a workstream folder with its own index and map of content, linked up into the root vault.
--dir string no With check: check a local folder (a worktree of the brain branch) instead of the branch's tip on the remote.

build

Build a Ready story or bug in a worktree with checkpoint commits per layer, verify each checkpoint, and open a PR.

Usage: aayu build [<issue>] [flags]

Field Value
In plain words Writes the code for a Ready story in small checked steps, one layer at a time, and opens a pull request.
Journey stage Build it
Accountable seat AI Native Engineer
Model lane build
Layers all
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates ready, budget, halt
Outputs pr, checkpoint-commits, progress-comment, delegation
Built in WP5.5
Skill build
Input Type Required Description
<issue> issue no Ready story or bug to build; required unless --next.
--next enum: ship, pick no The build-ready loop, with no model: ship lists the loop's own open PRs, oldest first, and changes nothing; pick blocks the loop's stale claims, then, under [build] in_flight, claims the first Ready story or bug (the current release's accepted baseline in its order, else priority, then age) and cuts its worktree.
--stop string no Stop this build for good: move the story to status:blocked with this reason and page its owner; the lease stays until it expires.
--resume bool no Resume from the last Aayudha-Checkpoint trailer.
--delegate enum: codex, cursor, claude, amp, auto no Hand the story to another agent's cloud agent with the delegation brief, or sync it: its PR, inspect's findings, and follow-ups (auto picks the cheapest adequate connected one).
--local bool no With --delegate: run the receiver's CLI on this machine in an aayu worktree, with no GitHub credential; aayu commits, verifies, pushes, and opens the PR.
--asked string no The person's own words asking for this story. An agent needs them to pick up a Ready story that did not come out of grill in this session; without them build stops with a warning before taking the story.
--decline string no Decline open items of the last session review, one ": " a line; the reason goes into the PR's session review summary, and the merge gate's inspect still judges them.

verify

Run the deterministic floors (coverage, SAST, secrets, deps, a11y, perf) and record results in a proof pack.

Usage: aayu verify [<pr>] [flags]

Field Value
In plain words Runs the fixed checks (tests, security, secrets, dependencies, accessibility, speed) and records the results.
Journey stage Prove it
Accountable seat AI Native Engineer
Policy owner Quality Architect
Model lane chore
Layers all
Writes as bot
Who reasons none
Surfaces cli, skill, mcp
Gates halt
Outputs floor-results, pack, map-drift, security-bugs
Built in WP4.3
Skill verify
Input Type Required Description
<pr> pr no Pull request to verify; defaults to the current worktree.
--floor string no Run only this floor.
--map bool no Only the feature-map drift check (WP4.5b): compare every .agents/skills/verify-*/ map with the source, run nothing, and exit 3 on drift.
--check string no Only the behaviour floor, on these feature-map checks: , ., or all (the sweep); a run outside the merge gate is a preview.
--maintain enum: drift, always no With --map or --check: post the maintain brief on the tracking issue for the agent app [verify] maintainer names, when the map drifted or a check failed (drift), or every time (always).
--security bool no Only the security floors (sast, secrets, deps, dast) on the checked-out commit, with no PR or story: what aayudha-security.yml runs on every push and nightly. With --ci, each failing finding files or updates one aayudha:security Bug.
--since string no With --security: scan secrets only in the commits after this revision (a push's before); without it, or with all zeros or an unknown revision, the whole history of HEAD.

inspect

Adversarially review a PR against its plan, pack, and criteria; return a structured disposition: merge, fix, or rebuild.

Usage: aayu inspect <pr> [flags]

Field Value
In plain words A model from another vendor, or an agent app you choose, reviews the pull request against every promise; aayu reads its reply as merge, fix, or rebuild.
Journey stage Prove it
Accountable seat Engineering Manager
Model lane review
Layers all
Writes as bot
Who reasons direct
Surfaces cli, skill, mcp
Gates authoritative-pack, budget
Outputs disposition (merge|fix|rebuild), findings, review-comments
Built in WP4.8
Skill inspect
Input Type Required Description
<pr> pr yes Pull request to inspect.
--mode enum: general, peer no general: one reviewer; peer: two reviewers of different families cross-check each other (default from [inspect]).
--dismiss string no Record the finding with this ID as dismissed in this repository, so inspect stops raising findings like it. Human identity only; never exposed over MCP.
--approve bool no As the [autonomy] approver, record your review of the PR's head on the ledger and post it as the human review the merge gate reads; a person-verified step, and the only way a human review counts. To approve several such PRs with one device code, use aayu inbox. Human identity only; never exposed over MCP.
--reason string no Why the finding is dismissed (with --dismiss), or what you checked (with --approve). Human identity only; never exposed over MCP.

ship

Squash-merge a PR after a green merge gate and a human pass, write the Complete section, and clean up.

Usage: aayu ship <pr> [flags]

Field Value
In plain words Merges a proven pull request after your yes, and writes down who approved what, on which evidence.
Journey stage Ship it
Accountable seat Engineering Manager
Model lane chore
Layers all
Writes as human
Who reasons none
Surfaces cli, skill
Gates merge-gate, human-pass
Outputs merge-commit, complete-section, status:merged
Built in WP5.5
Skill ship
Input Type Required Description
<pr> pr yes Pull request to ship.
--solo-bypass bool no Solo mode only (one human, no bot App): merge without a second person's approval, recorded in the PR, the ship record, and the actions log. Human identity only; never exposed over MCP.

release

Promote a Release along dev, rolling, main; stamp included stories released and trigger measurement.

Usage: aayu release <release> [flags]

Field Value
In plain words Moves shipped work up to a snapshot or stable release, after a full gate, and schedules the measurement.
Journey stage Release it
Accountable seat DevOps & DevEx Tinkerer
Model lane chore
Layers L09
Writes as human
Who reasons none
Surfaces cli, skill, mcp
Gates human-identity, stable-request, halt
Outputs tag, released-stories, release-notes
Built in WP7.8
Skill release
Input Type Required Description
<release> issue yes Release issue.
--to enum: rolling, main yes Branch to promote to.
--at string no With --to rolling: promote this dev commit instead of dev's newest, such as the newest one with tier-2 eval results for every gating group.

proof

Push, get, verify, or list proof packs on the ledger branch; comment is the merge gate's pack check.

Usage: aayu proof <action> [<story>] [flags]

Field Value
In plain words Stores, fetches, and checks the proof packs that hold the evidence for each change.
Journey stage Prove it
Accountable seat Quality Architect
Model lane chore
Layers all
Writes as bot
Who reasons none
Surfaces cli, skill, mcp
Outputs pack, verification-report
Built in WP4.2
Skill proof
Input Type Required Description
<action> enum: push, get, verify, list, comment yes Proof operation: push an advisory pack, get, verify, or list packs, or (merge gate only) comment: check the run's pack and keep its PR comment.
<story> issue no Story whose pack to operate on.
--media bool no Include proof media; needs a bucket in [proof] media, since media never go to the ledger or Git LFS.

ready

Validate a work item for Ready, label it status:ready, and post the Ready snapshot; --check is read-only.

Usage: aayu ready <issue> [flags]

Field Value
In plain words Checks that a work item is complete and freezes exactly what was agreed, so later edits are visible.
Journey stage Get a story Ready
Accountable seat Product Strategist
Model lane chore
Layers all
Writes as bot
Who reasons none
Surfaces cli, skill, mcp
Gates validator
Outputs status:ready, ready-snapshot, feature-baseline
Built in WP2.7
Skill ready
Input Type Required Description
<issue> issue yes Work item to make Ready.
--check bool no Validate only; write nothing.
--guard bool no Ready guard (the aayudha-ready-guard workflow): strip status:ready when the issue no longer validates or drifted from its snapshot.
--part enum: intent, spec, tech, ux no Feature part to baseline: a person approves its waiting draft, through GitHub's device flow every time; refused for an agent lane.
--request bool no With --part: draft the part's next baseline on the ledger (specs//baselines/-v.draft.json) and ask a person to approve it; never approves.

research

Gather pinned design references (URLs and IDs only) and user research for a Feature.

Usage: aayu research <feature> [flags]

Field Value
In plain words Collects design references and user research for a Feature.
Journey stage Design the screens
Accountable seat UX Researcher & Evolutionist
Model lane spec
Layers L01
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates halt
Outputs reference-set
Built in WP6.5
Skill research
Input Type Required Description
<feature> issue yes Feature to research.
--from path no Directory with stage.json: the references the host gathered (URLs and IDs only) and Markdown research notes.
--query string no Search Mobbin screens for this; needs [integrations.mobbin].
--platform enum: ios, android, web no Platform to search Mobbin on.

wireframe

Produce wireframes for a Feature's states from its research and criteria.

Usage: aayu wireframe <feature> [flags]

Field Value
In plain words Sketches the screens a Feature needs, from its research and promises.
Journey stage Design the screens
Accountable seat UX Researcher & Evolutionist
Model lane build
Layers L01
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates halt, budget
Outputs wireframes
Built in WP6.5
Skill wireframe
Input Type Required Description
<feature> issue yes Feature to wireframe.
--from path yes Directory with stage.json and one wireframe per state (SVG, HTML, Markdown, or an image).

mockup

Produce design-system mockups for a Feature from its wireframes.

Usage: aayu mockup <feature> [flags]

Field Value
In plain words Turns wireframes into mockups that use your design system.
Journey stage Design the screens
Accountable seat UX Researcher & Evolutionist
Model lane build
Layers L01
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates halt, budget
Outputs mockups
Built in WP6.5
Skill mockup
Input Type Required Description
<feature> issue yes Feature to mock up.
--from path yes Directory with stage.json and one SVG or HTML mockup per wireframe state, coloured only with design tokens.

prototype

Build a flagged, working prototype of a Feature with Code Connect mapping and a Figma screenshot diff.

Usage: aayu prototype <feature> [flags]

Field Value
In plain words Builds a working prototype behind a flag and compares it with the design.
Journey stage Design the screens
Accountable seat UX Researcher & Evolutionist
Model lane build
Layers L01, L02
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates figma-diff, halt, budget
Outputs prototype, feature-flag, figma-diff
Built in WP6.5
Skill prototype
Input Type Required Description
<feature> issue yes Feature to prototype.
--from path yes Directory with stage.json: the OpenFeature flag, Figma file, Code Connect sources, components, and each state's path and Figma frame.
--captures path no Diff these captures (captures.json with PNGs and computed styles) instead of rendering the states.

review

Critique UI with a model lane and a deterministic lane; dispositions recapture, rebuild, fix, or ship.

Usage: aayu review <pr> [flags]

Field Value
In plain words Critiques a pull request's screens with a model and with fixed accessibility checks.
Journey stage Design the screens
Accountable seat UX Researcher & Evolutionist
Model lane ui-review
Layers L01
Writes as bot
Who reasons hybrid (lane A direct)
Surfaces cli, skill, mcp
Gates budget
Outputs critique, disposition (recapture|rebuild|fix|ship)
Built in WP6.6
Skill review
Input Type Required Description
<pr> pr yes Pull request whose UI to review.
--deep bool no Run lane A at high effort when the lane's default effort is lower.

polish

Apply a review critique to a PR's UI and re-run review.

Usage: aayu polish <pr>

Field Value
In plain words Applies a design critique to a pull request and reviews it again.
Journey stage Design the screens
Accountable seat UX Researcher & Evolutionist
Model lane build
Layers L01
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates halt, budget
Outputs commits
Built in WP6.6
Skill polish
Input Type Required Description
<pr> pr yes Pull request to polish.

baseline

Capture visual baselines for a commit SHA.

Usage: aayu baseline [flags]

Field Value
In plain words Captures reference screenshots of a commit to compare later changes against.
Journey stage Design the screens
Accountable seat UX Researcher & Evolutionist
Model lane chore
Layers L01
Writes as bot
Who reasons none
Surfaces cli, skill, mcp
Gates halt
Outputs baseline-captures
Built in WP6.6
Skill baseline
Input Type Required Description
--sha string no Commit to baseline; defaults to HEAD.

experiment

Design an experiment for a Feature: hypothesis, metric, flag, and minimum sample size.

Usage: aayu experiment <feature> [flags]

Field Value
In plain words Designs an A/B test for a Feature: what you expect, what you measure, and how many people you need.
Journey stage Measure and learn
Accountable seat Revenue Architect
Model lane plan
Layers L03, L08
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates baseline, halt
Outputs experiment, feature-flag
Built in WP6.7
Skill experiment
Input Type Required Description
<feature> issue yes Feature (or Initiative) to experiment on.
--hypothesis string yes If we do X, the metric moves by Z because W.
--metric string yes Conversion event the experiment moves (a PostHog event name).
--flag string yes Feature-flag key that splits traffic: the PostHog flag key and GrowthBook tracking key.
--mde string yes Minimum detectable effect: an absolute rate change (0.02) or a relative one (10%).
--exposure string no HogQL predicate for the population the baseline counts; default every person with an event.
--alpha string no Two-sided significance level; default 0.05.
--power string no Statistical power; default 0.8.
--days int no Baseline window in whole UTC days before today; default 28.

readout

Read out an experiment's lift once it reaches minimum sample and write the Result.

Usage: aayu readout <experiment> [flags]

Field Value
In plain words Reads out an experiment once it has enough people, and writes down the measured lift.
Journey stage Measure and learn
Accountable seat Revenue Architect
Model lane spec
Layers L08
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates min-sample
Outputs result
Built in WP6.7
Skill readout
Input Type Required Description
<experiment> issue yes Experiment to read out.
--source enum: posthog, growthbook no Where the per-arm counts come from; default posthog.
--metric string no GrowthBook metric ID (with --source growthbook); PostHog uses the Experiment's Metric.
--from string no Start of the PostHog readout window (YYYY-MM-DD, UTC); default the Experiment's creation.

respond

Respond to an incident: propose an ops catalog action, execute it only through human approval, keep the timeline.

Usage: aayu respond <incident> [flags]

Field Value
In plain words Helps handle an incident: proposes a fix from your runbook, runs it only after a person approves, and keeps the timeline.
Journey stage Keep it running
Accountable seat Production Engineer
Model lane build
Layers L07, L09
Writes as human
Who reasons host
Surfaces cli, skill
Gates ops-catalog, environment-approval, human-identity
Outputs timeline, proposed-action, postmortem, linked-bug
Built in WP5.6
Skill respond
Input Type Required Description
<incident> issue yes Incident issue.
--action string no Catalog action to propose.
--params string no Action parameters as key=value pairs separated by commas.
--postmortem path no Blameless postmortem (Markdown) to check against the incident, its timeline, and its investigation note, and post on the incident (replaced in place).
--close bool no Close the incident: file its linked Bug (carrying the investigation note's implicated code and durable fix) and the retro entry; a Sev0 or Sev1 incident needs its postmortem first.

status

Roll up status, health, risk, proof coverage, decisions, and cost per Goal, Initiative, and Feature.

Usage: aayu status [<issue>] [flags]

Field Value
In plain words Rolls up progress, risk, proof, open decisions, and cost for each Goal, Initiative, and Feature.
Journey stage Explain it
Accountable seat Engineering Manager
Model lane chore
Layers all
Writes as bot
Who reasons none
Surfaces cli, skill, mcp
Outputs rollup, goal-comment, digest, streaks, work-in-flight
Built in WP2.8
Skill status
Input Type Required Description
<issue> issue no Goal, Initiative, or Feature to roll up; defaults to all Goals.
--digest bool no Send the digest through [notify].
--all bool no Iterate [fleet] repos.
--apply bool no Post the replace-in-place Goal comments and close Features the parent-close rule allows; with --streak, record new corrections on the ledger.
--streak bool no Compute the autonomy streak of every layer from merged-PR history instead of the rollups (WP5.7).
--work bool no List the work in flight instead: aayu worktrees (agent, story, branch, PR, age) and stories delegated to cloud agents (WP5.5b).

audit

Audit floors, proof coverage, waivers, decision SLAs, autonomy exceptions, and unlogged writes; write a reproducible report.

Usage: aayu audit [flags]

Field Value
In plain words Writes a report anyone can reproduce: checks, proof, waivers, deadlines, bypasses, and any write that skipped the log.
Journey stage Explain it
Accountable seat Auditor
Model lane review
Layers all
Writes as bot
Who reasons none
Surfaces cli, skill, mcp
Outputs audit-report
Built in WP7.6
Skill audit
Input Type Required Description
--since string no Window start (YYYY-MM-DD UTC or RFC 3339); default the cursor of the newest audit report on the ledger, else 7 days back.
--until string no Window end and GitHub event cursor (RFC 3339, exclusive); default now. With --since and --ledger it regenerates a report.
--ledger string no Ledger commit to read; default the ledger tip.
--out path no Also write the report to this file.
--replay string no Regenerate a report from the GitHub inputs snapshot at this ledger path (audit//…inputs.json); writes nothing.
--mark-merged string no Move these stories (e.g. 38-50) that merged without proof, before or after the merge gate, to status:merged with a comment saying which; no report.

retro

Compare estimates with observed delivery, corrections, floor misses, and cost; file findings as Feedback issues.

Usage: aayu retro [flags]

Field Value
In plain words Compares plans with what happened and files what to improve as feedback you can accept or reject.
Journey stage Measure and learn
Accountable seat Engineering Manager
Model lane spec
Layers all
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates halt
Outputs retro-report, feedback-issues, fix-layer
Built in WP7.6
Skill retro
Input Type Required Description
--since string no Window start (YYYY-MM-DD UTC or RFC 3339); default the cursor of the newest retro report on the ledger, else 7 days back.
--until string no Window end (RFC 3339, exclusive); default now.
--ledger string no Ledger commit to read; default the ledger tip.
--out path no Also write the report to this file.
--replay string no Regenerate a report from the GitHub inputs snapshot at this ledger path (retro//…inputs.json); files nothing.
--classify issue no Feedback issue to classify by the highest layer that can fix its correction for good (needs --layer and --reason); writes no report.
--layer enum: codebase, check, prose, review no With --classify: codebase (a type, invariant, or boundary), check (a lint rule, test, or CI check), prose (skill or AGENTS.md guidance), or review (what is surfaced for human review).
--reason string no With --classify: why this is the highest layer that can fix the correction for good.
--not-catchable string no With --classify: why no type, invariant, lint rule, or test can catch it; required for prose and review, and lets evolve rewrite a skill for a codebase or check correction.
--criterion string no With --classify and a layer other than prose: the Completion Goal criterion of the Story filed for it, \[evidence\] state: …; expected: …, whose proof is the new type, invariant, lint rule, test, or review surface.

measure

Measure a Goal or Initiative against its baseline from analytics exports or live cloud pulls and write the Result.

Usage: aayu measure [<issue>] [flags]

Field Value
In plain words Measures a Goal against its baseline, the same way as before, and writes the result into the Goal.
Journey stage Measure and learn
Accountable seat Data & AI Architect
Policy owner Revenue Architect
Model lane spec
Layers L08
Writes as bot
Who reasons none
Surfaces cli, skill, mcp
Gates baseline
Outputs result, snapshot
Built in WP7.2
Skill measure
Input Type Required Description
<issue> issue no Goal or Initiative to measure; without it, only the cohorts and North Star are reported.
--metric string no acquisition, activation, retention, referral, revenue, north_star, aayu:founder_minutes_per_pr (from the actions log on the ledger), or : [filter]; default the issue's Metric.
--from string no Window start (YYYY-MM-DD, UTC); default 28 days before --to.
--to string no Window end, exclusive (YYYY-MM-DD, UTC); default today.
--billing path no Billing export (CSV).
--appinsights path no Application Insights events export (JSON lines).
--aws path no AWS CloudWatch RUM events export (JSON lines).
--gcp path no Google Analytics 4 / Firebase BigQuery events export (JSON lines).
--live string no Pull the window's events live from configured cloud integrations instead of an export file: azure, aws, gcp, comma-separated.
--engine enum: sqlite, duckdb no Query engine for the snapshot; duckdb is optional and shelled out.

evolve

Turn accepted retro Feedback into a failing eval case, then a skill diff that passes it, opened as an agent-authored PR.

Usage: aayu evolve [flags]

Field Value
In plain words Turns accepted feedback into a test for a skill, then a skill change that passes it, for a person to review.
Journey stage Measure and learn
Accountable seat AI Native Engineer
Model lane build
Layers L05
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates eval-first, codeowner-review, halt
Outputs eval-case, skill-pr
Built in WP7.7
Skill evolve
Input Type Required Description
--skill string no Skill to evolve: skills//, or a stub under evals/skills//.
--feedback issue no Accepted Feedback issue filed by aayu retro that the change answers; without it, list the accepted retro Feedback.

brief

Explain work to an audience in a chosen register and purpose as a grounded, accessible HTML brief.

Usage: aayu brief <subject> [flags]

Field Value
In plain words Explains a piece of work to one audience in a short page, where every claim is checked against its sources.
Journey stage Explain it
Accountable seat Mentalist
Model lane spec
Layers all
Writes as bot
Who reasons hybrid (adversarial pass direct)
Surfaces cli, skill, mcp
Gates authoritative-pack, result
Outputs html-brief
Built in WP7.3
Skill brief
Input Type Required Description
<subject> issue yes Work item to brief on.
--register enum: eli5, ste, engineer, regulatory no Audience register.
--purpose enum: explain, ideate, innovate, close no Purpose of the brief.
--draft path no Markdown draft to check and render; without it, print the grounding to write from.

tell

Write docs, guides, changelogs, release notes, launch copy, or brand copy that cite only proven Features; publish is human-only.

Usage: aayu tell <kind> [flags]

Field Value
In plain words Writes docs, release notes, and launch copy in your brand's voice, linking only work that is proven.
Journey stage Explain it
Accountable seat Marketer & Documenter
Model lane spec
Layers L01
Writes as human
Who reasons host (publish requires the human identity)
Surfaces cli, skill, mcp
Gates authoritative-pack, human-identity
Outputs draft, published-content
Built in WP7.5
Skill tell
Input Type Required Description
<kind> enum: docs, guide, changelog, release, launch, brand yes What to write.
--from path no Markdown draft the host wrote; tell checks its claims and tone and tags its links. Without it, tell prints the brief: tone, proven Features, and UTM tags.
--tag string no Release tag the copy is about (release, changelog); publishing release notes also sets that GitHub Release's notes.
--campaign string no UTM campaign; default the tag, else -.
--site path no With docs: build the static docs site (README, getting started, verbs, skills, governance pages) into this new or empty directory; every page passes the claims check.
--publish bool no Publish the checked copy to the ledger (and the tag's GitHub Release); human identity only, logged. Human identity only; never exposed over MCP.

init

Set up a product repo: labels, issue types, forms, config, ledger branch, and optionally projects, gates, identity, integrations.

Usage: aayu init [flags]

Field Value
In plain words Sets up a repository for aayudha: labels, issue forms, config, and the records branch; more on request.
Journey stage Set up
Accountable seat Founder
Model lane chore
Layers L09
Writes as human
Who reasons none
Surfaces cli
Gates tty-confirm
Outputs labels, issue-types, forms, config, ledger-branch, state
Built in WP2.5
Input Type Required Description
--resume bool no Resume a partial run from .aayudha/state.json.
--projects bool no Create Projects v2 views.
--gates bool no Install gate workflows.
--identity bool no Create the GitHub App bot identity.
--integrations bool no Configure external integrations.
--verify-skill bool no Write the product's verify skill: an empty feature map and a control tool in the product's stack.

install

Install skill copies, lock.toml, MCP registration, and hooks for each host; shows a diff unless --apply.

Usage: aayu install [flags]

Field Value
In plain words Installs the aayudha skills, tools, and hooks into your agent, and sets up its cloud environment and loops.
Journey stage Set up
Accountable seat DevOps & DevEx Tinkerer
Model lane chore
Layers L09
Writes as human
Who reasons none
Surfaces cli
Gates tty-confirm
Outputs skill-copies, lock, mcp-registration, hooks, agent-environments, loops
Built in WP3.2
Input Type Required Description
--host enum: amp, cursor, claude, codex, copilot, all no Host to install for.
--apply bool no Write the changes instead of showing a diff.
--pin string no Skill version to pin.
--env bool no Set up agent environments instead: discover them from the code, ask what it cannot say, and show each host's generated configuration and UI values.
--verify bool no With --env: write the files and verify each host's environment in a clean container (setup cold, setup warm, the build and tests), fixing and retrying.
--cloud bool no With --env: prove the live cloud environment with a probe task where the host's CLI can (Amp, Codex) and record it.
--record string no With --env --host: record a probe reply copied from the host's UI; with --loops --host: record loops as set up there, =[,…] or all= (an empty ID forgets one).
--loops bool no Set up this repository's scheduled loops (loops/*.toml) in the one agent tool you pick from those detected: Amp's schedules and Cursor's Terraform with --apply, a ready prompt per loop for Claude Code and Codex; warns when another tool already runs them.
--run-now string no With --loops: test one loop now, once, with the tool's own CLI in this checkout. Human identity only; never exposed over MCP.

doctor

Check tools, tokens, identity, config, host installs, and existing CI; --fix re-syncs copies after showing a diff.

Usage: aayu doctor [flags]

Field Value
In plain words Checks your machine and setup, and says exactly what to fix.
Journey stage Set up
Accountable seat DevOps & DevEx Tinkerer
Model lane chore
Layers L09
Writes as human
Who reasons none
Surfaces cli, skill, mcp
Outputs report
Built in WP1.7
Skill doctor
Input Type Required Description
--fix bool no Re-sync copies and adapters after showing a diff.
--all bool no Iterate [fleet] repos.

chart

Chart an issue's data or AI design before planning: decisions, metrics, sources, platform, and retention; or evidence, permissions, abstention, and evals.

Usage: aayu chart <issue> [flags]

Field Value
In plain words Before a data or AI change is planned, works out with you which decisions it serves, which data or evidence answers them, and how to prove it right.
Journey stage Break it down
Accountable seat Data & AI Architect
Model lane spec
Layers L05, L07, L08
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates halt
Outputs chart-note, grounding
Built in WP5.1g
Skill chart
Input Type Required Description
<issue> issue yes Feature, Initiative, Story, or Bug whose data or AI design to chart.
--kind enum: data, ai yes data: decisions, metrics with grain and window, sources, platform and its trigger, retention and deletion; ai: simpler options, evidence and permissions, abstention, and an evaluation set.
--draft path no Markdown chart note the host's model wrote; chart checks every part, the stage's artefact, and every citation. Without it, chart prints the grounding and the outline.
--create bool no Post the checked note on the issue as one comment per kind, replaced in place on a rerun (through the actions log); needs --draft.

survey

Survey a codebase with no product docs: index it, check an evidence-backed analysis and backlog, and capture golden outputs for parity.

Usage: aayu survey [<path>] [flags]

Field Value
In plain words Reads a codebase nobody documented, says what it does with a citation for every claim, and drafts the backlog to modernise it.
Journey stage Shape the goal
Accountable seat Code Architect
Model lane plan
Layers all
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates validator, halt
Outputs index, fact-pack, survey-report, backlog, issues, golden, parity, compat, shadow, probes
Built in WP5.9
Skill survey
Input Type Required Description
<path> path no Checkout to survey; default the repository root.
--out path no Directory for the survey's files (index.json, SURVEY.md, backlog.md, golden/); default .aayudha/survey under the surveyed checkout.
--budget int no Module size in tokens (about four bytes each) when grouping files; default 20000.
--module string no Print one module's fact pack (files, targets, entry points, surfaces, markers, symbols, calls in and out) from the index; read-only.
--docs path no User manuals and notes from outside the checkout (a file or a directory of text, Markdown, HTML, man pages, or PDF through pdftotext), indexed as manual: documents a claim cites by line; their text is written under /manuals.
--draft path no Survey draft to check, whole or some of its sections (JSON: claims at the engineering, capability, and product levels, trap findings, the do-not-carry list, the compatibility contract, unknowns, answers, modernisation path): every claim cites the index, a manual, or a probe, or is marked unknown. Each section is saved with its findings under /sections and resumed by later runs; with every section present it writes survey.json and renders SURVEY.md.
--sections bool no Report the survey sections saved under /sections: which pass, which have problems, and which are missing or stale.
--backlog path no Backlog draft to check (JSON: Goal, Initiatives, Features, Stories, Bugs, and do-not-carry Decisions) against the work-item schema, the survey draft, and its compatibility contract; renders backlog.md and its review digest.
--create bool no With --backlog: file the reviewed backlog as issues through the actions log, skipping items already filed; needs --reviewed.
--reviewed string no With --create: the review digest of the exact backlog the person reviewed (printed by --backlog).
--limit int no With --create: the most issues one run files; default 25.
--golden path no Characterisation cases (JSON) to run against the legacy build (--bin), writing each case's stdout, stderr, and exit code with SHA-256 under golden/.
--parity path no Characterisation cases (JSON) to replay against the new build (--bin) and compare with the golden outputs; exit 3 on any difference.
--compat path no A legacy test suite as cases (JSON, each test with its suite and area) to run against the new build (--bin) after --golden ran it on the legacy build: scores passes per area, appends to compat-history.jsonl, exit 3 when a test the legacy build passes fails.
--bin string no With --golden, --parity, or --compat: the program the cases run as {bin}.
--run bool no With --golden, --parity, or --compat: run the cases' program; without it the cases file is only checked.
--shadow string no With --golden --bin --run: the new program, run beside the legacy one on the same inputs; reports every difference without golden files, exit 3 on any.
--probe bool no With --golden --bin --run: also run each case twice and under a changed time zone, locale, and HOME (and under strace when installed), writing non-determinism, environment dependencies, and files read and written to probes.json.
--check-bin string no With --probe: a sanitiser, checker, or differently optimised build of the legacy program; cases whose stderr carries a checker report, or whose stdout or exit code differs from the capture, are recorded.
--coverage path no With --probe: an lcov tracefile from running the cases under coverage; records the index's functions the cases never reach.

investigate

Investigate an incident from bounded telemetry queries to the deployed revision and the implicated code, and check the note; it proposes a mitigation, never runs one.

Usage: aayu investigate <incident> [flags]

Field Value
In plain words Works out what went wrong in production from your telemetry and the code that was actually deployed, and suggests a fix for a person to approve.
Journey stage Keep it running
Accountable seat Production Engineer
Model lane spec
Layers all
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates halt
Outputs investigation-note, grounding, query-log
Built in WP5.10
Skill investigate
Input Type Required Description
<incident> issue yes Incident issue.
--telemetry path no Sanitised OpenTelemetry export directory: traces.jsonl (OTLP JSON), logs.jsonl (JSON lines with trace_id), deploys.jsonl (deploy markers); read with no network. Give it or --source.
--source enum: sentry, posthog no Query the configured Sentry or PostHog project instead of an export, with a read-only key; needs --service. PostHog answers logs and exceptions only, and its exceptions are project-wide (error tracking has no service filter).
--service string no Service to scope every query to; default the only service in the export.
--environment string no Deployment environment to scope to; default the deploy marker's.
--revision string no Deployed revision; default the deploy marker serving the window, else service.version on the spans.
--from string no Window start (RFC 3339, UTC); default an hour before the incident started, or with --source and no start, 24 hours before --to. The window is at most 7 days.
--to string no Window end, exclusive (RFC 3339, UTC); default the export's last record, or now for --source.
--query string no Run one more bounded query and log it as qN: [by f,…] [where k=v …] [limit N] [bucket 5m].
--draft path no Investigation note (Markdown) to check: every part, the stage's artefact, cited evidence, two hypotheses, bounded queries, and a mitigation only proposed from the catalog.
--create bool no Post the checked note on the incident, replaced in place, and add a timeline line (through the actions log); needs --draft.

slo

Define SLOs and error budgets from the user's side, measure them from a sanitised export, and record the budget that gates release.

Usage: aayu slo [flags]

Field Value
In plain words Sets how reliable the product must be for its users, measures how much room for failure is left, and holds back risky releases when it runs out.
Journey stage Keep it running
Accountable seat Production Engineer
Model lane spec
Layers all
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates halt
Outputs slo-document, slo-status, query-log
Built in WP5.10
Skill slo
Input Type Required Description
--telemetry path no Sanitised OpenTelemetry export directory to measure each SLO in ops/slos.toml from (traces.jsonl), read with no network.
--service string no Service to scope the baseline queries to; default the only service in the export.
--query string no Run one more bounded query and log it as qN: [by f,…] [where k=v …] [limit N].
--draft path no SLO document (Markdown) to check: every part, the stage's artefact, cited evidence, objectives as percentages with windows, a burn-rate alert, the budget policy, and a proposed ops/slos.toml in a toml block that parses.
--create bool no Write the checked draft's toml block to ops/slos.toml in the checkout, for a pull request a person reviews; needs --draft.
--record bool no Record each SLO's measure and budget on the ledger (slo/status.json), which release reads; needs --telemetry.

runbook

Write and check runbooks: confirm a known failure with a bounded query, mitigate it only through the ops catalog, verify it, and roll it back.

Usage: aayu runbook [flags]

Field Value
In plain words Writes down how to spot and fix each known production problem with the approved actions, so whoever is on call can follow it.
Journey stage Keep it running
Accountable seat Production Engineer
Model lane spec
Layers all
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates halt
Outputs runbook, runbook-findings
Built in WP5.10
Skill runbook
Input Type Required Description
--draft path no Runbook entry (Markdown) to check: every part, the stage's artefact, cited evidence, an SLO named, a bounded confirm query, a catalog action, its rollback, and no executed change.
--create bool no Write the checked draft to ops/runbooks/.md in the checkout, for a pull request a person reviews; needs --draft.

scope

Plan a release's scope in its version milestone, draft it, have a person baseline it, hand it off, assign Feedback, and hold drift to the change budget.

Usage: aayu scope <release> [flags]

Field Value
In plain words Plans what a release contains, freezes it once a person accepts it, and stops later changes beyond the budget unless a person decides.
Journey stage Break it down
Accountable seat Product Strategist
Model lane plan
Layers all
Writes as bot
Who reasons host
Surfaces cli, skill, mcp
Gates scope-budget, halt
Outputs release-plan, scope-draft, scope-baseline, scope-drift
Built in v0.3.0
Skill scope
Input Type Required Description
<release> issue yes Release issue (Version vX.Y.Z) whose scope to plan; without another flag, scope reports the plan, its points, and its drift.
--add issue no Initiative, Feature, Story, or Bug to add to the release's milestone; after a baseline it counts as drift.
--drop issue no Item to remove from the release's milestone, so it rides a later release; after a baseline it counts as drift.
--assign issue no Feedback issue to assign with --to; sets its milestone and horizon label, never its body, and is not drift.
--to enum: this, next, backlog no With --assign: this release, the next release milestone, or the backlog.
--draft bool no Snapshot the plan on the ledger (releases//draft.json) and ask a person to accept it; refuses an unsized, XL, or unsliced plan.
--decision issue no Accepted Decision that names the Release: with --add, --drop, or --draft over budget, it asks a person to accept the change; never applies it.
--accept bool no Accept the Release's waiting request, a drafted baseline or a change over budget, through GitHub's device flow every time; aayu inbox shows the same card. Human identity only; never exposed over MCP.
--handoff bool no Hand the baselined plan off: write the Release's includes links and post the plan on it.

Plumbing commands

Plumbing commands are not verbs: they have no skill and no model lane.

Command Summary Seat Inputs
config Show, validate, or initialise layered configuration. DevOps & DevEx Tinkerer <action>, --origin
auth Show the human token and bot identity aayudha resolves, with scope warnings; set, delete, or list named secrets. DevOps & DevEx Tinkerer <action>, <name>
actions Tail, search, or verify the hash chain of the actions log. DevOps & DevEx Tinkerer <action>, <pattern>
models Show the resolved model for each lane and host. DevOps & DevEx Tinkerer <action>
mcp Serve verbs as MCP tools over stdio. DevOps & DevEx Tinkerer --skills
self-update Replace the binary with a signed, newer release; refuses downgrades and agents. DevOps & DevEx Tinkerer
upgrade Migrate repo config, lock, state, and skill copies to this binary's schema versions. DevOps & DevEx Tinkerer --apply
version Print the binary version. DevOps & DevEx Tinkerer
halt Stop every agent lane, loop, and workflow in the repo until resume. Founder --reason
resume Clear a halt. Founder
gc Prune stale worktrees and leases. DevOps & DevEx Tinkerer
uninit Remove what init created, by stored IDs. DevOps & DevEx Tinkerer --external
hook Entry point for host hooks; hooks call only aayu hook <name>. DevOps & DevEx Tinkerer <name>, --skills, --event
seat Add, remove, or list seats and their paired humans. Founder <action>, <seat>, --human
lfs-agent git-lfs custom transfer agent for S3/R2 storage. DevOps & DevEx Tinkerer
next Print the single best next step for this repository: the exact command to run and why. Engineering Manager
tour Guided first run: check this machine, then set the repository up at Level 1 in a few prompts; refused for agents. Founder
inbox Every human-only step waiting for you, one card at a time with the twin's counsel; Enter takes the recommendation and C clears the housekeeping. Refused for agents and needs a terminal, except --list. Founder --list
completion Print the shell completion script, generated from the registry, for bash, zsh, fish, or PowerShell. DevOps & DevEx Tinkerer <shell>