commands.md

Reference — Commands

Auto-generated by scripts/gen-docs-reference.mjs from commands/*.md frontmatter. Do not edit by hand — run node scripts/gen-docs-reference.mjs to refresh.

44 user-invocable commands.

Command	Model	Arguments	What it does
/aedt-bias-audit	sonnet	[slug]	HR-AI / AEDT bias audit. Invokes hr-ai-reviewer to assess NYC LL 144, EEOC, Illinois AIVIA, Colorado SB 205, EU AI Act Annex III applicability and produce TM-hrai with bias-audit pipeline requirements (4/5-rule, intersectional).
/agent-retire	haiku	[--archive-only] [--reason 'text'] | --list-candidates (idle agents)	Gracefully retire an LLM agent from the workforce. Archives prompt, removes from sync list, keeps verdicts for audit. Like firing a human — but reversible.
/agent-review	haiku	[agent-name] — empty = list all agents with summary | = drill into one agent. Flags: --since 30d (default) | --top-cost | --idle	Performance review for an LLM agent (or all agents). Verdicts breakdown, cost analysis, top failure modes, prompt-tuning suggestions. Like a human '1:1' but for AI workforce.
/api-contract-review	sonnet	[slug]	API platform contract review. Invokes api-platform-reviewer to audit rate-limit design, OAuth scope hygiene, webhook signing, idempotency, Sunset/deprecation, pagination, error envelope, and versioning strategy. Critical before v1 GA.
/audit	sonnet	[optional: 'eval' | 'lint' | focus area, e.g. 'focus on security']	Audit an existing codebase. Detects stack, finds gaps, creates tasks, generates PROJECT.md.
/board	haiku	[--port N] [--no-open] [--restart]	Open the great_cto admin board at http://localhost:3141 (Kanban, cost, pipeline, inbox, memory). Starts it in background if not running.
/burn	haiku	[service] — optional, filters to one service. Examples: /burn | /burn api	SLO burn rate — multi-window alerting that catches budget exhaustion before it happens. Uses .great_cto/slo-burn-history.log written by /digest.
/ccr	haiku	— the 12-char CCR id from a <!-- ccr: ... --> footer | (empty) = list recent recoverable items	CCR (Compressed Context with Retrieval) — recall the full original of context that great_cto compressed/filtered out, by its short id. The retrieval half of the compression layer.
/close-review	sonnet	[slug] — optional ARCH slug to review (defaults to latest)	Month-end close / GL compliance check — invokes accounting-reviewer to produce TM-accounting-{slug}.md with double-entry integrity, ASC 606 revenue-recognition, period-lock, and SOX ITGC gaps.
/coding-audit	sonnet	[slug]	Medical-coding / revenue-cycle compliance audit. Invokes rcm-reviewer to assess autonomous ICD-10-CM / CPT / HCPCS coding for False Claims Act exposure (upcoding/unbundling), NCCI edits + MUEs, medical necessity (LCD/NCD), modifier discipline, HIPAA minimum-necessary — and force a certified-coder (CPC/CCS) sign-off.
/cost	haiku	[period_days] | feature | agent — default: /cost 30. Examples: /cost 7 | /cost feature stripe-subscriptions | /cost agent architect	Cost & capacity health — LLM router savings, run-rate, cost-per-deploy, ROI per shipped feature, WoW/MoM delta. Pairs with /digest (delivery+DORA) and /burn (reliability).
/crystallize	sonnet	[approve GP-NNNN [--no-eval "reason"] | reject GP-NNNN | rollback GP-NNNN | prune | status]	Promote extracted incident knowledge into global patterns and agent improvements.
/digest	haiku	[days] [board] — e.g. '30 board' or 'Q2 board'	Weekly engineering digest. Velocity, incident trend, tech debt, ADR decisions, open gates, and a CTO recommendation. Add 'board' flag for board-report format.
/discover	sonnet	<product area, metric to improve, or 'what should we build next?'>	Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
/doctor	haiku	[--fix] — optional, emits remediation commands	Health check for great_cto. Shows pipeline state, missing artefacts, hook status, last run per agent, and permission-denied tail.
/exception	haiku	create --gate --reason "" [--scope S] [--days N] [--risk low|medium|high] | list | check	Signed gate-exception registry — replace ad-hoc --admin / --no-verify bypasses with an auditable, signed, expiring record (who · why · gate · scope · expiry). Create / list / check exceptions.
/gen-evals	haiku	— e.g. architect, qa-engineer, security-officer	Generate EVAL-*.md test cases for an agent from its prompt. Usage: /gen-evals [--count N]
/gov-metrics	haiku	[--since 30d] [--json]	Governance metrics — measure whether the gates actually work. Block rate, override/waiver rate, false-block proxy, R1-textual vs R2-mechanical share, and time-in-gate, computed from the verdict trail.
/help	haiku	[optional: topic — e.g. 'commands', 'agents', 'board']	Show great_cto commands, key concepts, and admin board URL. Use when you don't remember a command or you are new to great_cto.
/inbox	haiku	[optional: hours — default 24]	What needs your attention? Shows open gates, recent activity, blocked items, and pending decisions.
/learn	haiku	[focus] — optional: 'cost', 'security', 'architecture', etc. — narrows the learner's scope	Manually run the continuous-learner. Extract patterns from this session and write to .great_cto/lessons.md. Use when SessionEnd hook missed something or you want to capture a lesson mid-session.
/migrate	haiku	[--dry-run] — show what would change without writing	Migrate existing PROJECT.md to the latest great_cto schema — appends missing fields without touching existing values.
/msp-review	sonnet	[slug] — optional ARCH slug to review (defaults to latest)	MSP / managed-services compliance check — invokes msp-reviewer to produce TM-msp-{slug}.md with client-isolation, credential-vaulting, SLA-tracking, and incident-escalation gaps.
/oncall	haiku	who | handoff | schedule <member1,member2,...> | escalate	On-call rotation management. Who's on duty, shift handoff notes, escalation paths. Reads from .great_cto/oncall-schedule.md and OWNERSHIP.md.
/ownership	sonnet	map | show | set | verify	Service ownership matrix. Who owns what: team, tech lead, on-call, SLA. Auto-detects from git history. Generates CODEOWNERS.
/poc	sonnet	| decide | extend | status	Start a hypothesis-driven POC with hard timebox. Skips 80% of the production pipeline; forces ship/pivot/kill decision at expiry.
/prd	sonnet	<feature idea, problem statement, or 'upload doc'>	Create a Product Requirements Document — conversational intake, 8-section output. Run BEFORE architect to lock WHAT and WHY before the team decides HOW.
/procurement-review	sonnet	[slug] — optional ARCH slug to review (defaults to latest)	Procurement / source-to-pay compliance check — invokes procurement-reviewer to produce TM-procurement-{slug}.md with three-way match, segregation-of-duties, OFAC-screening, and SOX procurement-controls gaps.
/promote	sonnet	[target: mvp|production, default: production]	Promote a POC to MVP/production. Runs the full audits that POC-mode skipped. Required before any POC can see production.
/prompt-evolve	sonnet	[--lesson "text"] — e.g. /prompt-evolve security-officer --lesson "fewer false positives on TODOs"	Closed prompt-evolution loop: turn a lesson into a candidate agent prompt, gate it on held-out evals, promote only if it beats the baseline. SIA Meta→Target→Feedback ported to great_cto.
/recall	haiku	— e.g. 'jwt', 'quota', 'board', 'npm'	Search session history by concept keyword. Returns matching sessions with relevant bullets. Usage: /recall
/release	sonnet	notes [version] | changelog [from..to] | docs | sync	Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync
/resume	haiku	[project-path] — defaults to current directory	Resume a previous session. Reads recent session logs, open tasks, and last decisions — gives Claude full context without re-explaining the project.
/review	sonnet	[PR/branch name | --deep | trace | trace ]	12-angle code review + skeptical triage (3-round + arbiter) for security/reliability P0/P1 findings, OR traceability tree. Default: review current branch vs main. --deep: triage ALL P0/P1 angles (not just security). With trace <id>: render REQ → IMPL → TEST tree for impact analysis. Creates or closes gate:code for approval-level: strict.
/rfc	sonnet	new "title" | list | show | close accept|reject [reason] | comment "text"	RFC process for cross-team decisions. Create, track, and close RFCs. Accepted RFCs auto-create ADRs.
/save	haiku	[description] — e.g. 'implemented auth flow' (auto-inferred if omitted)	Save current session. Writes a session log with what was done, decisions made, and what's pending. Optional: commit & push.
/sec	sonnet	[subcommand] [args...] — default: status. Examples: /sec | /sec status 7 | /sec threat stripe-subscriptions | /sec sbom | /sec incident "creds leaked"	Security umbrella: posture metrics, threat model, SBOM, incident workflow. Subcommands: status (default) | threat | sbom | incident | rotate.
/skillify	sonnet	[name] — e.g. 'incident-review' or 'api-contract-gen' (auto-prompted if omitted)	Capture a repeating pattern as a reusable skill. Run when you notice the same 5+ steps appearing 3+ times across sessions or agents. Produces a skills//SKILL.md file.
/spec	sonnet	[project description or 'retrofit' for existing codebases]	Spec Driven Development: interview → requirements.md + design.md + tasks.md. Run before writing any code.
/start	sonnet	[free-form project description]	Set up a new project. Describe what you're building — agents do the rest.
/tax-review	sonnet	[slug] — optional ARCH slug to review (defaults to latest)	Tax-filing compliance check — invokes tax-reviewer to produce TM-tax-{slug}.md with MeF e-file schema, Form 8879, PTIN/Circular 230, and IRC §7216 consent gaps.
/trace	haiku	| feature | --json	Requirement → use-case → task → test traceability (NaCl graph value, no Neo4j). Trace one bd node's rationale (upstream) + impact (downstream), or audit a whole feature's chain for coverage gaps. Reads beads relationships.
/upl-check	sonnet	[slug]	Unauthorized-practice-of-law (UPL) + legal-services compliance review. Invokes legal-reviewer to audit UPL gating, IOLTA/trust accounting, attorney-client privilege, conflict-of-interest screening, and e-filing redaction. Required before shipping any client-facing legal-SMB feature.
/voice-compliance	sonnet	[slug] — optional ARCH slug to review (defaults to latest)	Voice/telephony compliance check — invokes voice-ai-reviewer to produce TM-voice-{slug}.md with TCPA, STIR/SHAKEN, state recording-consent, EU AI Act Art. 50, and synth-voice deepfake-law gaps.