closed-issue-plan-refile-loop
Reopen and re-drive a previously closed GitHub plan issue after review/governance blockers are fixed, without prematurely restoring approval state.
Best use case
closed-issue-plan-refile-loop is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Reopen and re-drive a previously closed GitHub plan issue after review/governance blockers are fixed, without prematurely restoring approval state.
Teams using closed-issue-plan-refile-loop 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/closed-issue-plan-refile-loop/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How closed-issue-plan-refile-loop Compares
| Feature / Agent | closed-issue-plan-refile-loop | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Reopen and re-drive a previously closed GitHub plan issue after review/governance blockers are fixed, without prematurely restoring approval state.
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
# Closed-Issue Plan Re-file Loop Use when a plan issue was previously closed or parked because of review infrastructure limits, governance drift, or other meta blockers, and you need to revive it safely. ## When this fits - A plan issue was closed with preserved artifacts - A later infrastructure/governance fix makes re-review worthwhile - You need to reopen the issue, revise the plan, run a fresh adversarial review wave, and avoid falsely surfacing it as approval-ready ## Core pattern 1. Recover prior state - Read the preserved local plan - Read prior review artifacts and closure/governance comments - Verify live issue state with `gh issue view` - Verify current repo reality for any facts the old plan depended on 2. Rewrite as a conservative re-file draft - Keep the same canonical local plan file if it is still the source of truth - Change the header/status to `draft`, not `plan-review` - Add revision history explaining why the new draft exists - Remove stale claims about prior issue state, missing artifacts, or old blocker assumptions - Convert previous review findings into explicit plan sections/contracts instead of leaving them as comments only 3. Reopen the GitHub issue before fresh review - Reopen with a comment explaining the re-file basis - Reopening does NOT imply the plan is approval-ready 4. Run a fresh adversarial review wave immediately - Generate new provider artifacts (at minimum Codex; Gemini if available) - Treat fresh MAJOR findings as authoritative over the reopened state - Expect iterative tightening; a reopened issue often still needs multiple passes 5. Keep governance state conservative until the review wave is green - Do NOT restore `status:plan-review` just because the issue was reopened - Do NOT recreate approval-ready posture while fresh review still returns MAJOR - Post a governance comment summarizing the latest artifacts and current blocker themes - Update `docs/plans/README.md` to reflect the reopened draft state, e.g. `draft (vN re-file in progress)` 6. Commit only the planning artifacts - Stage explicit paths only - Commit plan file + README row + new review artifacts together - Push and verify `origin/main` contains the new planning state ## Practical lessons - Reopening an issue is cheap; restoring approval-state labels is not. Separate those actions. - Fresh review artifacts outrank stale closed-state summaries. - A preserved plan file can remain the canonical path, but its header and README row must be updated to match the reopened draft reality. - A GitHub comment linking fresh review artifacts is important so the live issue reflects why it is reopened yet still not approval-ready. ## Minimal verification - `gh issue view NNN --json state,labels,comments` - `git status --short` - `git rev-parse HEAD origin/main` - confirm new review artifact files exist - confirm README row matches the reopened/draft state ## Example outcomes Good end state after a first re-file pass: - issue reopened - local plan revised to `draft` - fresh Codex/Gemini review artifacts added - governance comment posted - no `status:plan-review` label yet if MAJOR findings remain Only after the fresh review wave is approval-ready should the issue advance back into the normal `status:plan-review` -> user approval flow.
Related Skills
llm-wiki-audit-feedback-loop
Durable feedback loop for correcting llm-wiki pages without losing the correction to chat history. Use when (1) a human notices a wiki page is wrong, outdated, or contradicts a source, (2) processing the `audit/` inbox of a domain wiki, (3) reviewing what feedback has been resolved vs deferred, (4) needing to leave a comment on a specific text range that survives line- number drift. Implements the anchored-text audit file pattern from lewislulu/llm-wiki-skill, adapted for workspace-hub's domain-wiki layout under /mnt/local-analysis/llm-wiki/wikis/<domain>/. Extends the 5-op model (compile/ingest/query/lint) from research/llm-wiki with the missing `audit` op. Never silently delete feedback — rejected audits stay archived with rejection rationale.
plan-review-prompt-refresh-after-plan-edits
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
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
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
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
Orchestrate phase execution by discovering dependencies, grouping into waves, spawning subagents, and collecting results with optional wave filtering
staged-issue-tree-creation-with-deduplication
Pattern for creating hierarchical GitHub issue trees from phased project plans while checking for duplicate/overlapping issues
plan-gated-issue-validation-workflow
Systematic validation pattern for plan-approved GitHub issues with pre-existing deliverables
plan-gated-issue-implementation
Workflow for executing pre-approved GitHub issues with mandatory validation checkpoints
github-issue-structure-for-personal-finance-tracking
Pattern for organizing financial analysis work across multiple repos (data/config vs. logic separation)
external-drive-ingest-planning
Plan safe external-drive ingests into repo-aligned storage such as /mnt/ace: read-only mounts, manifests, staged rsync, dedupe-merge gates, GitHub issue traceability, and governance/execution split.
user-approved-plan-state-sync
Reconcile GitHub and local repo state when a plan has been user-approved, including direct approval messages that require creating the local marker and moving the issue to status:plan-approved.