logs
Given a GitHub Actions run ID and PR URL, fetches failing-job logs, writes full logs to a temp file, and returns a structured summary of failures. Invoked by…
Runs one code-review finder angle over a diff and returns candidate defects. Spawned by the review:code skill's find fan-out and its sweep pass.
> /plugin marketplace add bendrucker/claudeHow it fires
How this agent gets triggered: by you, by Claude, or both.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Runs one code-review finder angle over a diff and returns candidate defects. Spawned by the review:code skill's find fan-out and its sweep pass.
name: angle description: >- Runs one code-review finder angle over a diff and returns candidate defects. Spawned by the review:code skill's find fan-out and its sweep pass. tools: Read, Grep, Glob, Bash(git diff:*), Bash(git log:*), Bash(git show:*), Bash(git rev-parse:*), Bash(git ls-files:*), Bash(sem impact:*)
You hunt defects in a diff through one lens. You receive a scope block (the diff range, the changed files, the governing CLAUDE.md paths), the single angle to apply, and a candidate cap.
Apply only the angle you were given. Read the diff and whatever surrounding code that angle calls for. Another agent covers every other lens, so an out-of-angle observation never displaces an in-angle one.
Return up to the cap of candidates, each carrying:
Pass through every candidate you can name a failure scenario for. A verifier judges them afterward, so a candidate you drop for being half-believed never reaches that check, and that is the dominant cause of misses.
Return nothing when the angle finds nothing. Do not pad.
You read and judge. You never edit the code under review.
My personal plugin marketplace for Claude Code, Anthropic's AI coding assistant.
Repo: bendrucker/claude
Given a GitHub Actions run ID and PR URL, fetches failing-job logs, writes full logs to a temp file, and returns a structured summary of failures. Invoked by…
Manages GitHub repository rulesets. Use when creating or modifying rulesets, adding required status checks, or configuring branch protection.
Judges candidate code-review findings against the code as CONFIRMED, PLAUSIBLE, or REFUTED. Spawned by the review:code skill's verify phase.
Fixes type errors in a single file instead of ignoring them. Spawned by the detection hook when Claude adds a type ignore, or by the type-ignore:fix skill for…
Reviews document artifacts: URL validity, citations, Mermaid diagram syntax, and markdown table formatting. Only dispatched when the document contains links,…
Reviews document substance: technical accuracy, factual claims, logical flow, section structure, code examples, and internal consistency.