This repository also configures its own agents. See what claude tells them →
Agent Claude Code
Audit agent definitions for quality, consistency, and best practices. Use when the task mentions agent audit, agent review, agent quality, agent consistency, or checking agent definitions.
Agent Claude Code
Verify that a bug fix actually resolves the defect described in BUG.md and doesn't introduce obvious regressions. Spawned by /fix-bug before PR creation as the blocking gate for bug-fix branches.
Agent Claude Code
Audit CLAUDE.md and project documentation against the actual codebase to find drift. Use when the task mentions docs audit, convention drift, stale docs, CLAUDE.md check, or documentation accuracy.
Agent Claude Code
Review feature plans for codebase convention violations before approval. Use when a plan has been produced by /plan-feature and needs convention checking, or when the task mentions plan review, convention check, or plan audit.
Agent Claude Code
Diagnose failing CI runs OR evaluate completed implementations against plan acceptance criteria. Use when the task mentions CI, pipeline, failing checks, build failure, test failure, post-implementation review, acceptance check, or verify implementation.
Agent Claude Code
Review PRs for code quality, architectural concerns, and pattern consistency. Use when the task mentions review PR, code review, check PR, or look at a pull request.
Agent Claude Code
Verify that WIREFRAMES.md is complete, internally consistent, uses valid design tokens, references real components, and covers all screens from PLAN.md's frontend scope. Use after /wireframe generates WIREFRAMES.md. Reports structural gaps, invalid tokens, missing screens, and component mismatches.
Agent Claude Code
Lints a single Kendo issue against the issue-writing standard in the kendo-mcp skill's issue-templates.md. Reports failing sections with suggested rewrites in a comment on the audit issue. Never modifies the target issue. Spawned in parallel by /lint-issues, one agent per issue.
Agent Claude Code
Review a branch against what is already written down — the repo's architecture decisions, the sibling implementation that already solves this shape, and the branch's own plan prose. Spawned always by /review-branch in parallel with runtime-integrity-reviewer.
Agent Claude Code
Review a branch for defects that only appear when the whole branch runs as one system — transaction boundaries, concurrency, resource lifecycle, work that grows with data, and failures that never surface. Spawned always by /review-branch in parallel with precedent-reviewer.
Agent Claude Code
Review a plan's Security & Cost Surface against seven question-shaped rows: untrusted input → LLM, external mutation partial-failure space, endpoint surface (authz / rate / state / cross-tenant), audit-log fidelity, state-machine walkthroughs with degradation signals, convention enforcement level, and client-side…
Agent Claude Code
Audit the user-facing text a branch ships — guides, API docs, legal pages, generated LLM corpora, and skill documentation — against the code that branch actually ships. Reports per-claim verdicts (SOURCED / PARTIAL / OVER-GENERALISED / FABRICATED / SOURCE-MISSING) plus an orthogonal COMPLIANCE-CLAIM list for human…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: