From egregore
Orchestrates the QUALITY pipeline stage for egregore work items, running code review, unbloat, test updates, and doc updates. Use before creating a PR or when reviewing another agent's PR.
How this skill is triggered — by the user, by Claude, or both
Slash command
/egregore:quality-gateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- Running quality checks on egregore work items
make lint directly)Orchestrate the QUALITY stage of egregore's pipeline. Each quality step runs convention checks from the codex and invokes mapped skills.
| Step | Conventions | Skills | Modes |
|---|---|---|---|
| code-review | C1,C2,C3,C4,C5 | pensive:unified-review | self, pr |
| unbloat | - | conserve:unbloat | self |
| code-refinement | - | pensive:code-refinement | self |
| update-tests | - | sanctum:update-tests | self |
| update-docs | C5 | sanctum:update-docs, scribe:slop-detector | self |
The orchestrator invokes this skill with:
When mode is "self-review":
git diff --name-only main...HEADconventions/codex.ymlconventions.pyIf blocking findings exist:
if no findings:
verdict = "pass"
elif all findings are severity "warning":
verdict = "pass-with-warnings"
elif blocking findings remain after auto-fix:
verdict = "fix-required"
Record verdict in manifest decisions:
{
"step": "code-review",
"chose": "pass-with-warnings",
"why": "2 warnings (C4: noqa in hooks), 0 blocking"
}
By default the loop runs indefinitely and autonomously: a
fix-required verdict is recorded but does not, on its own,
stop the item from advancing. This preserves the historical
hands-off posture.
When config.pipeline.completion_integrity is true, the
verdict becomes a gate the agent cannot talk its way past:
fix-required verdict is reported to the orchestrator as
a step failure, so the item cannot advance to the ship
stage with unresolved blocking findings. It retries in place
and, on exhausting max_attempts, is marked failed and
the overseer is alerted (never silently completed).auto_merge:
the PR is prepared but left open.This binds "done" to the verifier (convention checks plus the
mapped review skills), not to the agent's own say-so. Rationale
and evidence:
docs/research/2026-07-01-the-coming-loop-agentic-harness-guardrails.md
and .claude/rules/prefer-invariants-over-fallbacks.md. The flag
is off by default; enabling it is a deliberate choice to keep a
human as the final judge.
When mode is "pr-review":
gh pr diff <number> --name-onlypensive:unified-review on the diffMap findings to GitHub review:
gh api POST review with
event "APPROVE"Comment format per finding:
[egregore:{convention_id}] {message}
Convention: {convention_name}
Severity: {severity}
Work items may have a quality_config field:
{
"skip": ["unbloat"],
"only": ["code-review", "update-docs"]
}
skip: list of steps to skip (run all others)only: list of steps to run (skip all others)only takes precedenceNot all conventions run on every step. The routing table above defines which conventions apply to which step. The quality gate filters the loaded codex accordingly before running checks.
npx claudepluginhub athola/claude-night-market --plugin egregoreValidates code quality via tests, linting, security; auto-fixes issues; generates commits; multi-agent reviews; creates PRs. Use after features to ship confidently.
Prepares pull requests by running quality gates, drafting descriptions, and validating tests. Use when completing a feature and ready for review.
Use when finishing tasks, shipping significant features, or before landing changes to ensure work meets standards through automated review