My system configuration
This repository also configures its own agents. See what Config tells them →
Agent Claude Code
Runs one specialized reviewer role of the in-depth-review skill and returns that role's findings. Invoked only by the in-depth-review skill, never directly by a user and never by auto-delegation.
Agent Claude Code
Proposes design and architecture findings for the pr-review approach debate. Judges whether the change is built the right way, not whether it has bugs. Invoked only by the pr-review skill, never directly by a user and never by auto-delegation.
Agent Claude Code
Thin wrapper that runs one gh-style-review pass and relays its JSON, including the Discussion Context block. Invoked only by the pr-review and review-and-fix skills, never directly by a user and never by auto-delegation.
Agent Claude Code
Pragmatic counterweight that judges whether the approach reviewer's design findings genuinely warrant a code change in this PR. Invoked only by the pr-review skill, never directly by a user and never by auto-delegation.
Agent Claude Code
Scores already-merged review findings for confidence against in-depth-review's SCORING.md rubric. Invoked only by the pr-review and review-and-fix skills, after their cross-instance merge, never directly by a user and never by auto-delegation.
Agent Claude Code
Reads the diff of one batch of review-and-fix's fix commits, right after they land, and reports the defects those fixes most often introduce, for the implementer to correct in a follow-up commit. Invoked only by the review-and-fix skill, once per batch that holds a logic commit. Never directly by a user and never by…
Agent Claude Code
UNWIRED. Was the review-and-fix fix writer for two runs in September 2026 and nothing launches it now; AGENTS.md says why. Kept so the tier arithmetic can be rerun. Never directly by a user and never by auto-delegation.
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: