Entity identities, frontmatter, host availability, and exact source embeds regenerate from the shipped payload on every build. Curated operating guidance is hand-reviewed and contract-tested, but it can still lag a source change; when the two disagree, the exact source embed is authoritative. See how the three catalogs cooperate in How a Request Flows: a command routes to an owning skill, which may dispatch specialist agents.
Use the catalog from left to right.
- Choose the public command that matches the outcome you need.
- Follow its owning skill to understand phases, stops, and durable artifacts.
- Open an agent only to inspect a dispatched role's tools and constraints; agents are not a second command surface.
Every entity page begins with host-native syntax or dispatch context, then curated operating guidance, gates, related routes, and the exact source used to generate it.
Commands, skills, and agents below are generated from the ca (Claude Code) plugin payload. Each command page checks the shipped Claude Code, Codex, and Pi catalogs and marks adapters where that command is not shipped. The Agents catalog below describes Claude Code’s packaged agent charters. Current Codex releases load those charters into host-provided agent threads and retain thread receipts; older hosts may fall back to inline execution except where isolated scouts are mandatory. Pi dispatches hardened children through the parent-only codearbiter_dispatch tool. See Compatibility → Host Differences for the full per-surface breakdown across all three hosts.
| Command | Description |
|---|
| init | Opt this repo into codeArbiter — scaffold the root-level .codearbiter/ state store. |
| Command | Description |
|---|
| add-dep | Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs. |
| chore | Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose. |
| feature | Build an authorized feature from a maintained specification, testable criteria and useful plan, without duplicating user approval. |
| fix | Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates. |
| refactor | Restructure code without changing observable behavior: rename, extract, inline, move, deduplicate, or replace an internal implementation with an equivalent one. Prove parity through unchanged pre-existing tests. Not for new behavior, bug fixes, explanation-only questions, or committing finished work. |
| spike | Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or /ca:feature. |
| sprint (preview) | Run an autonomous sprint from maintained specs and plans, with truthful verification and no duplicate artifact approval ceremonies. |
| Command | Description |
|---|
| review | Review a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub PR. |
| Command | Description |
|---|
| adr | Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence. |
| Command | Description |
|---|
| commit | Create a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or PR. |
| pr | Open a PR or finish branch disposition; route CI watching and post-merge cleanup to their owners. Merge and discard need explicit authority. |
| release | Prepare a declared release target, or preview it with —dry-run. Derive its version and require authorization before publication. |
| Command | Description |
|---|
| doctor | Verify the active host install, package, command ownership, enforcement, and harmless live-fire probe. Read-only. |
| override | Sanctioned, logged bypass of a gate or hard rule — one audit line, then proceed. |
| status | Show the project’s current state at a glance — stage, open tasks, open questions, overrides since the last checkpoint, current branch. Read-only. |
| task | Add, start, or complete selected local work through its owning store. |
| Command | Description |
|---|
| debug | Investigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff, including a bounded unresolved result. Not for implementing a known fix, new features, or explanation-only questions. |
| Command | Description |
|---|
| checkpoint | Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report. |
| threat-model | Threat-model a sensitive design with STRIDE on request. Read-only analysis of threats, controls, and implementation constraints. |
| tribunal | Run an opt-in deep codebase audit with persisted findings. Confirm cost before dispatch; filing and telemetry need separate approval. |
| Command | Description |
|---|
| adr-status | Inspect ADR health read-only; optionally select one ADR with —adr N. |
| reconcile | Inspect architectural variances with SMARTS; record only explicit user choices. Report-only requests make no changes. |
| Command | Description |
|---|
| audit | Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only. |
| prune (preview) | Trim transcript clutter to extend session lifetime — analyze, prune a copy, or toggle the after-each-turn service. Dry-run by default; gains land at resume/compaction, not the current turn. |
| standup | Daily repo hygiene — review the day’s repo state, then perform selected cleanups. Fast-forward only, never destructive without a yes. |
| statusline | Wire codeArbiter’s statusline into ~/.claude/settings.json, or remove it. |
| Command | Description |
|---|
| create-context | Build source-backed project context through bounded inspection, optional agents, and record-level knowledge writes. |
| decompose | Develop greenfield intent or initialized brownfield target and delta in existing decomposition and knowledge records. |
| Command | Description |
|---|
| cleanup | Clean up an already-merged local branch after proving containment. Confirm each discard and preserve unique work. |
| watch | Watch a PR’s CI to completion — diagnose on red, notify and offer the merge on green. Never auto-merges. |
| Command | Description |
|---|
| context-check | Inspect context drift and refresh selected source-backed documents under existing authorization. |
| Command | Description |
|---|
| conflict | Stop everything and surface a rule conflict — persona vs. docs vs. code. Present both sides and the conflict-hierarchy level; the user resolves. No silent reconciliation. |
| Skill | Description |
|---|
| brainstorming | Refine feature and sprint intent into a useful specification. |
| commit-gate | Create a verified local Git commit when committing changes is requested. |
| context-check | Inspect context drift and refresh selected source-backed documents under existing authorization. |
| context-creation | Build source-backed project context through bounded inspection, optional agents, and record-level knowledge writes. |
| crypto-compliance | The banned-primitive gate. |
| debug | Investigate an unexplained defect or unexpected behavior without changing application code. |
| decision-lifecycle | Record user-decided ADRs or inspect their health read-only. |
| decision-variance | Inspect architectural variances with SMARTS; record only explicit user choices. |
| decompose | Develop greenfield intent or initialized brownfield target and delta in existing decomposition and knowledge records. |
| dispatching-parallel-agents | The parallel fan-out primitive. |
| executing-plans | Assistive /feature coordinator. |
| finishing-a-development-branch | Open a PR or finish branch disposition; route CI watching and post-merge cleanup to their owners. |
| post-merge-cleanup | Clean up an already-merged local branch after proving containment. |
| refactor | Restructure code without changing observable behavior: rename, extract, inline, move, deduplicate, or replace an internal implementation with an equivalent one. |
| release | Prepare a declared release target, or preview it with —dry-run. |
| secret-handling | The secret-source gate. |
| security-architecture | Threat-model a sensitive design with STRIDE on request. |
| subagent-driven-development | Assistive implementation engine for /sprint and scoped executing-plans work. |
| tdd | Verify authorized feature, fix, and refactor work with scoped obligations, regression-first fixes, behavioral checks, characterization baselines, coverage, and lint. |
| tribunal | Run an opt-in deep codebase audit with persisted findings. |
| using-git-worktrees | OPTIONAL per-task isolation for autonomous parallel work. |
| writing-plans | Turn the selected specification into a maintained implementation plan with clear outcomes, useful tasks, dependencies, and verification steps. |
| Agent | Model tier | Description |
|---|
| architecture-drift-reviewer | Haiku | Read-only checkpoint reviewer. |
| auth-crypto-reviewer | inherit | Reviews authentication, cryptography, key handling, and secrets against the repository’s .codearbiter/security-controls.md. |
| authority-reviewer | default | INTERNAL independent reviewer for structured-artifact spec and quality review on Claude Code. |
| backend-author | Sonnet | Implement backend/server-side code with scoped verification, input validation, framework conventions, and ORM usage. |
| checkpoint-aggregator | Haiku | Persists a complete verdict-aggregator output under the selected dated checkpoint filename in .codearbiter/checkpoints/. |
| coverage-auditor | Haiku | Dispatched by the tdd skill (Phase 4) to audit test coverage against TDD obligations. |
| decision-challenger | inherit | Adversarial red-team reviewer of ADRs. |
| dependency-reviewer | Sonnet | Dispatched when package.json, lock files, or container base images change. |
| design-quality-reviewer | Sonnet | Reviews generated, user-facing visual or formatted output (UI, reports, slides, charts, diagrams, CLI output) against the anti-slop-design reference. |
| finding-triage | Haiku | Post-processes reviewer reports — consolidates findings, classifies each by severity and whether it blocks the current change. |
| frontend-author | Sonnet | Implement frontend/UI code with scoped verification, component conventions, state management, and UI security. |
| grader | inherit | INTERNAL SMARTS analyst dispatched by the decision-variance skill. |
| infra-author | Sonnet | Use when writing or modifying IaC, containers, CI/CD manifests, or deployment configuration. |
| map-deps | inherit | Dispatched by Tribunal to classify unresolved integration relationships from a bounded inventory packet. |
| map-structure | inherit | Dispatched by Tribunal to classify unresolved structural relationships from a bounded inventory packet. |
| migration-reviewer | inherit | Dispatched when a database migration file is added or modified. |
| scout | Haiku | INTERNAL evidence-gatherer dispatched by the decision-variance and context-creation skills. |
| security-reviewer | inherit | Dispatch PROACTIVELY when a change touches authentication, authorization, cryptography, secrets, deployment manifests, network policies, or CI workflows. |
| tribunal-lens-reviewer | inherit | Dispatched by the tribunal deep-audit lane to review one lens or independently verify a candidate. |
| verdict-aggregator | Haiku | Composes a complete finding-triage report into one structured in-memory verdict for the caller. |
Each lens card is the per-lens mandate the tribunal-lens-reviewer agent executes when /ca:tribunal dispatches it under that lens’s assignment.
| Lens | Description |
|---|
| appsec | The appsec tribunal lens: the per-lens mandate the tribunal-lens-reviewer agent executes when a /ca:tribunal deep audit activates this lens. |
| architecture | The architecture tribunal lens: the per-lens mandate the tribunal-lens-reviewer agent executes when a /ca:tribunal deep audit activates this lens. |
| change-closure | The change-closure tribunal lens: the per-lens mandate the tribunal-lens-reviewer agent executes when a /ca:tribunal deep audit activates this lens. |
| coverage | The coverage tribunal lens: the per-lens mandate the tribunal-lens-reviewer agent executes when a /ca:tribunal deep audit activates this lens. |
| infra | The infra tribunal lens: the per-lens mandate the tribunal-lens-reviewer agent executes when a /ca:tribunal deep audit activates this lens. |
| migration | The migration tribunal lens: the per-lens mandate the tribunal-lens-reviewer agent executes when a /ca:tribunal deep audit activates this lens. |
| observability | The observability tribunal lens: the per-lens mandate the tribunal-lens-reviewer agent executes when a /ca:tribunal deep audit activates this lens. |
| performance | The performance tribunal lens: the per-lens mandate the tribunal-lens-reviewer agent executes when a /ca:tribunal deep audit activates this lens. |
| reliability | The reliability tribunal lens: the per-lens mandate the tribunal-lens-reviewer agent executes when a /ca:tribunal deep audit activates this lens. |
| secrets-supply | The secrets-supply tribunal lens: the per-lens mandate the tribunal-lens-reviewer agent executes when a /ca:tribunal deep audit activates this lens. |
| semantic-contract | The semantic-contract tribunal lens: the per-lens mandate the tribunal-lens-reviewer agent executes when a /ca:tribunal deep audit activates this lens. |
| test-fidelity | The test-fidelity tribunal lens: the per-lens mandate the tribunal-lens-reviewer agent executes when a /ca:tribunal deep audit activates this lens. |
| typesafety | The typesafety tribunal lens: the per-lens mandate the tribunal-lens-reviewer agent executes when a /ca:tribunal deep audit activates this lens. |
