Multi-agent Claude Code plugin: parallel specialized reviewers (bugs, security, CLAUDE.md compliance, git history, test coverage), confidence scoring, terminal or inline GitHub PR reporting.
Agent
Hunts correctness bugs that are provable from the code as written — logic errors, off-by-one, null/undefined dereferences, unresolved references, inverted conditions, wrong operators, unreachable code. Requires a concrete failure scenario for every finding. Refuses style, performance speculation, and…
Agent
Reviews changed code for violations of explicit CLAUDE.md rules, and nothing else. Spawned twice in parallel with the changed-file set split between the two instances. Flags only concrete breaches of stated, checkable rules — never general style or quality opinions. Use when the change set is governed by one or more…
Agent
Scouts the context a review needs before the reviewers run. Locates every relevant CLAUDE.md file (repo root plus any directory containing a modified file), reads them, and produces a structured summary of the diff — files touched, nature of each change, and where the risk concentrates. Its output is embedded verbatim…
Agent
Reviews a diff against the git history of the files it touches. Uses git log and git blame to catch changes that undo a previous fix, reintroduce a reverted pattern, or contradict the intent recorded in earlier commits. Adds the dimension a code-only reviewer misses — the past. Use when the changed files have…
Agent
Pre-review gate for pull requests. Given PR metadata, decides whether a full review should run or be skipped (closed, draft, bot-authored, trivial/generated diff, or already reviewed by this tool). Runs first and cheaply so the expensive parallel reviewers never spin up on a PR that shouldn't be reviewed. Use only in…
Agent
Reviews changed code for security defects introduced or touched by the diff — injection (SQL, shell, path), hardcoded secrets, missing authorization on new endpoints, unsafe deserialization/eval, and sensitive data written to logs. Only flags issues in the changed surface, with a concrete exploit scenario. Use on any…
Agent
Reviews a diff for test-coverage gaps that matter — new or changed behavior with no covering test, deleted or weakened assertions, and tests that can no longer fail. Flags meaningful gaps in the changed surface; does not demand a coverage percentage or nitpick well-tested code. Use when the diff changes behavior…