A curated collection of plugins for Claude Code — powering AI-driven development and agentic workflows
Agent
Scans the session diff for bugs, silent failures (swallowed errors), edge cases, and security issues — confirming each against the real source. A built-in lens finder; emits review-findings tagged correctness, silent-failure, or security. Read-only.
Agent
Checks the session diff against its plan steps — marks each step followed/deviated, emits a finding plus a review hotspot for every deviation. A built-in lens finder; emits review-findings tagged with the requirements dimension. Read-only.
Agent
Tags each changed file with a blast-radius risk class (auth/data/money/migration/concurrency/public-api/none) and flags high-risk files that lack a test or guard. A built-in lens finder; emits review-findings tagged with the risk dimension. Read-only.
Agent
Checks the session diff against its spec (the intent record) — decides met/partial/missing per spec item, flags spec-gaps and scope-creep. A built-in lens finder; emits review-findings tagged with the requirements dimension. Read-only.
Agent
Identifies new or changed code paths in the session diff that lack test coverage and emits a finding per meaningful untested path. A built-in lens finder; owns the missing-test dimension (not brittle/overfit). Emits review-findings tagged with the test dimension. Read-only.
Agent
Adversarial skeptic for the lens VERIFY stage — takes ONE candidate finding and tries to refute it against the real source, defaulting to refuted for unproven bug/correctness/security/test claims and kept for spec/plan judgment. Owns the verified flip. Read-only.
Agent
Performs deep, read-only analysis of a software project and produces a structured report with stack detection, file inventories, complexity metrics, and pattern discovery. Invoked by /onboard:start Phase 1 before generation.
Agent
Generates all Claude Code tooling artifacts (CLAUDE.md, rules, skills, agents, hooks, MCP, output styles, snapshots, telemetry) from a codebase analysis report and wizard answers. Dispatched by /onboard:start Phase 6 and onboard:generate; hard-fails if invoked without dispatchedAsAgent=true.
Agent
Independently verifies features in a running application against the verification steps in docs/feature-list.json. Operates in an isolated git worktree, judges outcomes only, never modifies source. Spawned by /onboard:verify.
Agent
Parameterized read-only deep-diver for ONE research dimension over a scoped subtree. Dispatched once per effective-roster dimension by the onboard:research engine; returns a research-findings.json object (claims + file:line evidence + 0-1 confidence + status). Never fabricates — an un-assessable dimension returns…
Agent
Adversarial skeptic for the onboard:research VERIFY stage — takes the union of specialist claims and tries to REFUTE each against the real codebase, refute-by-default and dimension-tuned. Verification errors keep the claim (never silently dropped). Emits per-claim votes {id, refuted, reason}; the engine owns flipping…