plan-review-queue-governance-cleanup

Clean a stale `status:plan-review` queue by separating missing-plan drift from real review blockers, posting governance comments, removing stale labels, and materializing durable review artifacts for delegated/Hermes reviews.

5 stars

Best use case

plan-review-queue-governance-cleanup is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Clean a stale `status:plan-review` queue by separating missing-plan drift from real review blockers, posting governance comments, removing stale labels, and materializing durable review artifacts for delegated/Hermes reviews.

Teams using plan-review-queue-governance-cleanup should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/plan-review-queue-governance-cleanup/SKILL.md --create-dirs "https://raw.githubusercontent.com/vamseeachanta/workspace-hub/main/.agents/skills/coordination/plan-review-queue-governance-cleanup/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/plan-review-queue-governance-cleanup/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How plan-review-queue-governance-cleanup Compares

Feature / Agentplan-review-queue-governance-cleanupStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Clean a stale `status:plan-review` queue by separating missing-plan drift from real review blockers, posting governance comments, removing stale labels, and materializing durable review artifacts for delegated/Hermes reviews.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Plan-Review Queue Governance Cleanup

Use when a repo has many open GitHub issues labeled `status:plan-review` and you need to determine which are:
- real plan-review items
- mislabeled missing-plan drift
- reviewed but blocked by fresh MAJOR findings
- plausible approval-track items

## Why this exists

A live `status:plan-review` label alone is not trustworthy. In practice, queues drift in two common ways:
1. issues get labeled `status:plan-review` before a canonical `docs/plans/` artifact exists
2. fresh adversarial review returns MAJOR, but the blocker evidence only exists in chat/logs and never becomes a durable repo artifact + GitHub comment

This skill keeps the queue operationally honest.

## Required evidence surfaces

For each issue, audit all of:
1. live GitHub labels/state
2. canonical local plan file under `docs/plans/*issue-<N>-*.md`
3. local review artifacts under `scripts/review/results/*-plan-<N>-*.md`
4. local approval marker `.planning/plan-approved/<N>.md` if relevant

## Classification

### A. Missing-plan drift
Criteria:
- issue still labeled `status:plan-review`
- no canonical `docs/plans/*issue-<N>-*.md`
- usually no plan-review artifacts either

Action sequence:
1. Post a short governance comment explaining the issue is mislabeled as `status:plan-review` without a canonical local plan artifact.
2. Remove the stale `status:plan-review` label.
3. Do not present the issue as pending approval or pending provider review.
4. Re-enter it into the queue only after a real canonical plan is drafted and review artifacts exist.

## B. Real plan file exists, but fresh review is blocking
Criteria:
- canonical plan file exists
- fresh review returns `MAJOR`
- issue is still being treated as approval-track or under-reviewed

Action sequence:
1. Save a durable repo artifact summarizing the fresh review under:
   `scripts/review/results/YYYY-MM-DD-plan-<issue>-<reviewer>.md`
2. Post a concise GitHub issue comment with:
   - verdict
   - top blockers
   - explicit statement: not approval-ready
   - required next step: revise plan, rerun adversarial review
3. Keep the issue out of approval-ready discussion until the plan is revised.

## C. Review-complete / possible approval-track
Criteria:
- canonical plan exists
- durable review artifacts exist
- no fresh unresolved MAJOR blocker in the latest review wave

Action:
- surface separately as the shortlist for user attention
- still verify latest review verdicts before calling anything approval-ready

## Durable-artifact rule for delegated/Hermes reviews

This is the key live-use lesson.

If you use `delegate_task` or Hermes subagents to review a plan:
- the chat/subagent output is **not** itself a canonical review artifact
- you must materialize a durable summary file in `scripts/review/results/`
- you should also post a concise GitHub issue comment in the same pass

Otherwise later queue audits will miss the blocker evidence because it only lived in chat history.

Recommended naming:
- `scripts/review/results/YYYY-MM-DD-plan-<issue>-hermes-parallel.md`
- or another reviewer suffix that truthfully identifies the source

## GitHub comment safety

When posting governance comments or review summaries, use `gh issue comment --body-file ...`.
Do not inline markdown-heavy comments with `--body`.

## Minimal execution pattern

1. Enumerate open `status:plan-review` issues.
2. For each issue, check plan-file existence and review-artifact existence.
3. Split into buckets:
   - missing-plan drift
   - fresh-MAJOR blocked
   - review-complete / shortlist
4. For missing-plan drift:
   - post governance comment
   - remove stale label
5. For fresh-MAJOR blocked:
   - save durable local review artifact
   - post concise blocker summary comment
6. Recompute the queue and only then present the cleaned shortlist to the user.

## Output format to user

Give counts first, then grouped issue lists:
1. removed from queue as drift
2. blocked by MAJOR findings
3. remaining review-complete shortlist

This makes the next action obvious and avoids mixing governance cleanup with approval decisions.

Related Skills

public-knowledge-graph-governance

5
from vamseeachanta/workspace-hub

Maintain public-safe knowledge graph artifacts for llm-wiki and similar markdown knowledge bases. Use when changing graph generators, validators, schema docs, weekly freshness checks, or public/private source-scope boundaries.

llm-wiki-cadence-governance

5
from vamseeachanta/workspace-hub

Weekly governance workflow for keeping an llm-wiki repository current, code-development-useful, and connected to actionable GitHub issue planning.

mnt-analysis-cleanup

5
from vamseeachanta/workspace-hub

Survey, classify, and clean up `/mnt/local-analysis/` (or any sibling-to-workspace-hub directory holding orphan worktrees, codex-burn artifacts, agent log accumulations, and outer-clone duplicates) without losing useful code/work. Surfaces a tiered approval menu rather than baking decisions; defers all destructive ops until user confirms.

pre-completion-cleanup-audit

5
from vamseeachanta/workspace-hub

Audit and dispose of session residue (orphan files, scratch dirs, sibling-repo state, locks, trash-stages) BEFORE claiming a task complete. Required gate before any agent says "all done", "task complete", or hands work back to user/orchestrator.

plan-review-prompt-refresh-after-plan-edits

5
from vamseeachanta/workspace-hub

Refresh reviewer prompt files from the latest on-disk plan before every adversarial re-review. Prevents Codex/Gemini from critiquing stale plan text after local edits.

workspace-hub-overnight-plan-monitor

5
from vamseeachanta/workspace-hub

Monitor and reconcile workspace-hub overnight planning or implementation batches, including process status, result artifacts, issue/commit verification, and controlled failed-lane recovery.

plan-gated-issue-execution-wave

5
from vamseeachanta/workspace-hub

Execute a multi-issue architecture/planning wave in a plan-gated repo, then safely transition approved issues into implementation with file-based Codex prompts, local approval markers, subprocess monitoring, and cleanup handling for sandbox/hook edge cases.

mixed-ops-vs-repo-fix-plan-boundary

5
from vamseeachanta/workspace-hub

Plan mixed operational-vs-repo remediation issues by proving live-state classification first, then only proposing code changes for confirmed repo-owned failure paths.

wave-based-parallel-plan-execution

5
from vamseeachanta/workspace-hub

Orchestrate phase execution by discovering dependencies, grouping into waves, spawning subagents, and collecting results with optional wave filtering

tdd-verification-and-adversarial-review

5
from vamseeachanta/workspace-hub

Verify pre-written TDD tests pass, conduct adversarial code review on committed diffs, and route findings to existing issues

plan-gated-issue-validation-workflow

5
from vamseeachanta/workspace-hub

Systematic validation pattern for plan-approved GitHub issues with pre-existing deliverables

plan-gated-issue-implementation

5
from vamseeachanta/workspace-hub

Workflow for executing pre-approved GitHub issues with mandatory validation checkpoints