grimoire

Author, validate, and package grim-publishable artifacts — skill directories, rule files, agent definitions, MCP server descriptors, and bundle TOMLs. Use when creating or editing an artifact for grim build or grim release; when choosing frontmatter or catalog metadata fields; when adding claude, opencode, copilot, codex, cursor, kiro, junie, gemini, zed, or amp vendor keys; or when grim build fails validation with exit code 65.

Drive the grim CLI — the OCI package manager for AI skills, rules, agents, and bundles. Use when installing, updating, searching, or publishing AI-config artifacts with grim; when composing grim init, config, add, lock, install, update, status, context, fetch, describe, search, tui, mcp, build, release, publish, login, logout, or completions commands; when configuring settings, multiple registries, or qualified alias/repo references; or when resolving registries, project vs global scope, client targets, or offline mode.

Craft effective AI agent configuration — skills, rules, agents, and instructions — for any AI coding client. Use when writing or reviewing a SKILL.md, rule file, or agent definition; when deciding between a skill, rule, hook, or always-on instruction; when a config file grows past its context budget; or when a skill description fails to trigger.

Use for branch, PR, or diff review before landing on main. Tier (`low | auto | high | max`) scales breadth from single reviewer to adversarial panel with architect + SOTA-gap + Codex cross-model gate. Triggers: "review", "/swarm-review", pre-merge checks.

Use when the user says "codex review", "/codex-adversary", "adversarial review", "cross-model review", or asks for a different-model second opinion on a diff or plan artifact. Complements `/swarm-review` via Codex-CLI. Scopes: code-diff (default), plan-artifact (gate for `/swarm-plan`).

Use to implement a plan artifact from `/swarm-plan`, or a free-text implementation task with contract-first TDD + Review-Fix Loop. Tier (`low | auto | high | max`) scales builder model, loop rounds, review breadth, and Codex code-diff gate.

Use for feature planning, task decomposition, multi-perspective research, or ADR scaffolding. Tier (`low | auto | high | max`) scales research depth, architect model, and review breadth. Canonical research primitive for AI config / ADR work.

Use when the user says "finalize", "/finalize", "prepare this branch for main", "clean up history", "squash the branch", or landing a branch on `main`. Rewrites Checkpoint working-phase commits into clean Conventional Commits before fast-forward merge. Flags: `--squash-all`, `--dry-run`.

A release-cutting playbook — version bump, changelog, tag, publish checklist. Published ALONE under a deep nested repo path (playbooks/ci/release/) so the TUI tree folds the single-child chain into one node.

A retired diff reviewer kept only to exercise grim's deprecation surface end to end. Use code-reviewer instead.

Use when a bug is reported, something is broken, an error or crash needs fixing, a wrong output appears, or a regression shows up — guides Grimoire's Reproduce → Root-Cause → failing-test-FIRST → Fix → Verify discipline and will not let the fix begin until a failing regression test is recorded. Use also when the user says "bugfix", "/bugfix", "fix this bug", or "something is broken".

Sketch a module layout and pick design patterns for a new feature. Use when asked to plan an architecture, choose between approaches, or document a design decision before implementation. The walkthrough starts from the feature's user-visible behaviour and works inward, mapping each responsibility onto a module with a single reason to change, then weighs candidate patterns against the codebase's existing conventions rather than introducing novelty for its own sake. It covers strategy traits for swappable behaviour, facade seams that keep business logic out of the CLI layer, and three-layer error chains so batch operations diagnose failures per item. Every recommendation closes with the rejected trade-offs, so the design note doubles as an auditable decision record. This deliberately verbose description gives the manual rig one artifact whose detail pane overflows a small terminal — open it in grim tui and scroll with the arrow keys or j/k.

Review a diff for SOLID/DRY violations, missing tests, and risky changes. Use when asked to review a pull request, audit a patch, or check code quality before merge.

Draft a Conventional Commit message from staged changes. Use when the user asks to commit, save progress, or write a commit message.

A minimal smoke-test skill. Use to verify a grimoire install/transform round-trip end to end with the smallest possible artifact.

Use when task involve design spec, ADR, one-way-door decision, or evaluate trade-offs between architectural approaches. Invoke before implementation when requirements span subsystems or decision hard reverse. Trigger: /architect.

Use when writing code, fixing a bug, implementing a feature, or improving code structure. Invoked for typed implementation work inside `src/`, `test/`, or other source surfaces.

Use for code review, quality audits, SOLID/DRY consistency checks, pattern audits across the codebase, or verifying anti-pattern compliance across a scope.

Use when the user says "commit", "/commit", "save progress", or asks to land working changes on a feature or worktree branch. Grimoire working-phase posture — minimises commit count, can amend rolling Checkpoints, offers a one-time PR prompt. For pre-merge cleanup, use `/finalize`.

Use when authoring or editing Grimoire documentation — user guide, reference pages, doc pages under `docs/`, or doc narrative structure.

Use when auditing the freshness of `.claude/rules/subsystem-*.md` files against current codebase state, or when a subsystem has undergone significant change.

Use when user asks "what's next" or "next step". Prints next slash command from current state via a sonnet subagent. Flags: `--clear`, `--list`.

Use when designing test suites, writing acceptance tests, validating an implementation against a spec, or planning test coverage before implementation. Trigger: /qa-engineer.

Use for security audits, threat modelling, vulnerability assessment, or evaluating the attack surface of a new capability before merge. Trigger: /security-auditor.