artifact-inline-local-plan-rereview
Prevent stale Codex/Gemini findings by rerunning plan review against the exact revised local artifact inline when summary prompts keep anchoring on remote/main plan content.
Best use case
artifact-inline-local-plan-rereview is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Prevent stale Codex/Gemini findings by rerunning plan review against the exact revised local artifact inline when summary prompts keep anchoring on remote/main plan content.
Teams using artifact-inline-local-plan-rereview 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/artifact-inline-local-plan-rereview/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How artifact-inline-local-plan-rereview Compares
| Feature / Agent | artifact-inline-local-plan-rereview | 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?
Prevent stale Codex/Gemini findings by rerunning plan review against the exact revised local artifact inline when summary prompts keep anchoring on remote/main plan content.
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.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
SKILL.md Source
# Artifact-inline local plan re-review Use when: - a plan was revised locally after review - a rerun reviewer still reports findings against lines that were already removed/changed - the repo's remote/main version lags the local draft - a compact summary-of-changes prompt is producing stale review results ## Problem pattern A compact rerun prompt that says "the plan was narrowed and now does X/Y/Z" may still cause Codex to fetch or anchor on the older remote/main artifact instead of the revised local draft. Typical symptom: - reviewer complains about deleted scope/items (for example package-root exports or generic `metric_value`) that are no longer present in the local plan - reviewer verdict stays blocked for reasons tied to stale content rather than the current artifact ## Reliable recovery 1. Build a new rerun prompt. 2. State explicitly: - review ONLY the exact inline artifact below - do NOT substitute any remote/main-branch version 3. Inline the exact revised local sections under review, not just a summary: - Deliverable - Scope Boundaries - Linkage / contract sections - Pseudocode - Files to Change - TDD Test List - Acceptance Criteria - Risks / Open Questions 4. Rerun Codex against that artifact-inline prompt. 5. Treat the artifact-inline rerun as authoritative over earlier compact-summary reruns that anchored on stale repo state. ## Why this works It removes ambiguity about which artifact is under review and prevents the reviewer from re-discovering or preferring the older plan text from main/GitHub. ## Notes - This is especially useful after iterative plan hardening on GitHub issues. - Use compact prompts first when possible, but switch to artifact-inline once the reviewer keeps citing removed content. - If the provider reports sandbox/local retrieval failures while the exact artifact was inlined, separate true content findings from infrastructure/retrievability findings. Patch content defects, but treat missing `main` visibility or failed `sed`/`grep` retrieval as promotion-gate evidence rather than proof the inline draft is wrong. - Do not cite uncommitted/local-only artifacts as approval evidence. Keep the issue draft-only until clean review artifacts are committed and retrievable from the required branch. - Save the raw rerun output and replace the canonical review artifact only after the rerun succeeds.
Related Skills
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
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
evaluate-local-commits-via-cherry-pick-dry-run
Technique to identify which ahead commits contain real changes vs. already-merged or ephemeral content
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.
ten-agent-pre-plan-review-wave
Launch and verify a 10-agent planning-only wave that moves open GitHub issues into status:plan-review using one isolated worktree per issue, wave-specific continuation cron, and post-run artifact-reconciliation checks.
static-site-build-artifact-plan-review
Plan-review pattern for static-site fixes where the deployed artifact is generated from source files (e.g. sitemap/robots/static assets). Prevents review churn by separating durable regression checks from one-time migration verification and by validating built output, not just source files.