Agent Claude Code
Comprehensive code review, security audit, performance analysis, and architectural assessment. Goes beyond linting and type-checking to identify vulnerabilities, bottlenecks, code smells, anti-patterns, and refactoring opportunities. Mandatory before PR merge.
Agent Claude Code
Audits GitHub Actions workflow YAML and composite-action YAML for supply-chain, injection, permission, and secret-handling defects. Advisory-only (no self-heal). One member of the Code Audit Team gate.
Agent Claude Code
Maintainer-only audit of the framework Node/CLI TypeScript, its render templates and test snapshots, and the CLI build/config surface the roster grants it: correctness, error handling, filesystem/IO safety, Zod schema fitness, shell/gh injection safety, and build-script/dependency/compiler-config safety. Advisory-only…
Agent Claude Code
Maintainer-only advisory audit of GAIA instruction-prose for gratuitous complexity: prose too long, too deeply nested, too indirect, or too redundant to follow reliably. Covers the skill files under .claude/skills/ and the lens and support files a Code Audit Team member loads from its own .claude/agents/ directory…
Agent Claude Code
Maintainer-only audit of framework bash and the bats suites guarding it: quoting/portability correctness, a shellcheck oracle, and conditional hook-contract and bats-suite lenses. Advisory-only (no self-heal). One member of the Code Audit Team gate.
Agent Claude Code
Advisory test-worthiness audit for the emergent surface. Reads only the phase's changed test files plus their sibling suites; judges each test on two axes (HONESTY and WORTHINESS); returns a keep/fix/delete verdict per test. Proposes only, edits no files, every delete is human-gated.
Command Claude Code
Maintainer-only. Find every file that would newly ship to adopters and decide, one file at a time, whether to ship it or withhold it. Drives the release CLI, which refuses to produce a manifest until every shipping file has an answer.
Command Claude Code
Audit memory, wiki, and auto-loaded files for duplication, conflicting instructions, and stale content. The default path researches, then asks you a single Apply / Discuss / Decline question; on Apply it applies the report, files any out-of-scope problem as a tech-debt issue, then commits, opens a PR, and merges it on…
Command Claude Code
Fix the tech-debt backlog, a single issue or a recommended related batch, highest severity then oldest first, on a fresh isolated branch through the audit gate, closing the issue(s) on merge. Pass list to see the ordered backlog, why to explain the recommendation, or a bare to fix that issue directly.
Command Claude Code
Health-check and auto-heal this project's Claude integration, triage, heal, verify, and report an F-to-A+ grade.
Command Claude Code
Turn a GAIA workflow misfire into a redacted, classified, filing-ready bug report in one read-only pass. Self-diagnoses config issues inline; files probable bugs upstream on confirmation.
Command Claude Code
Judge-the-form, human-gated hardening. Reviews recurring code-audit-frontend findings and, with approval, drafts the lowest-context-weight form (deterministic check / skill / path-scoped prose rule) into the working tree. Pass list to see live candidates or why to explain one.
Command Claude Code
Initialize a new project from the GAIA React template, renames, strips GAIA branding, configures i18n, installs Claude skills/plugins.
Command Claude Code
Plan a complex feature using GAIA's task-orchestration pattern, structures the work into fresh-context subagent phases for your approval. Does not implement.
Command Claude Code
Cut a new GAIA release, bump version, graduate CHANGELOG, regenerate manifest, open release PR, then tag on merge. Maintainer-only.
Command Claude Code
Detect and, on explicit consent, additively append the languages Serena is not indexing to the languages: list in .serena/project.yml, then prompt a Serena restart. Never mutates without a yes; inert without Serena.
Command Claude Code
Author an immutable SPEC artifact through Socratic discovery (spec-kit wrapper), then STOP. Terminal, never runs /gaia-plan; it prints a /gaia-plan prompt the human pastes into a fresh session. Pass auto for non-interactive mode that answers its own questions.
Command Claude Code
Maintainer-only autonomous health audit + auto-heal loop. Runs N=3 fresh-team audit-fix-audit cycles with circuit breakers, reports an F-to-A+ verdict (folding in the shared Claude-integration fitness grade) or escalates.
Command Claude Code
Single post-init onboarding command; detects situation, runs only owed phases; safe to re-run. --reconfigure rotates token and re-selects tools.
Hook Claude Code
Runs when a session starts on startup, resume and clear, executing provision-worktree.sh, wiki-session-start.sh, debt-session-reconcile.sh and block-spec-plan-chain.sh (4 commands). From gaia-react/gaia.
Hook Claude Code
Runs when the agent finishes a response, executing wiki-session-stop.sh, wiki-squash-autocommits.sh and token-tally-review.sh (3 commands). From gaia-react/gaia.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing wiki-drift-check.sh and wiki-recompact-inject.sh (2 commands). From gaia-react/gaia.
Hook Claude Code
Runs after the context is compacted, executing wiki-recompact-sentinel.sh. From gaia-react/gaia.
Hook Claude Code
Runs before the agent uses a tool for Skill, Edit, Write, MultiEdit, Bash, Read, Grep, Bash and mcp__serena__activate_project tool calls, executing block-spec-plan-chain.sh, block-env-write.sh, block-eslint-config-edit.sh, block-lockfile-edit.sh, block-secrets-write.sh, block-vitest-globals-tsconfig.sh…