overnight-pre-plan-review-wave-artifact-drift
Run overnight planning-only waves for issues before status:plan-review, and reconcile cases where GitHub state advances but plan/review artifacts land in a sandbox or remote branch instead of the active local worktree.
Best use case
overnight-pre-plan-review-wave-artifact-drift is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Run overnight planning-only waves for issues before status:plan-review, and reconcile cases where GitHub state advances but plan/review artifacts land in a sandbox or remote branch instead of the active local worktree.
Teams using overnight-pre-plan-review-wave-artifact-drift 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/overnight-pre-plan-review-wave-artifact-drift/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How overnight-pre-plan-review-wave-artifact-drift Compares
| Feature / Agent | overnight-pre-plan-review-wave-artifact-drift | 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?
Run overnight planning-only waves for issues before status:plan-review, and reconcile cases where GitHub state advances but plan/review artifacts land in a sandbox or remote branch instead of the active local worktree.
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
# Overnight pre-plan-review wave artifact drift Use when: - the goal is to move open issues from pre-`status:plan-review` into `status:plan-review` - you want 4 parallel Codex planning workers overnight - the main checkout is dirty or already carrying unrelated state - you need planning only, not implementation ## Core workflow 1. Create a fresh planning worktree from `origin/main`. 2. Select up to 4 open issues that lack both `status:plan-review` and `status:plan-approved`. 3. Write one prompt per worker plus a master summary. 4. Restrict worker writes to planning artifacts only: - `docs/plans/YYYY-MM-DD-issue-NNN-*.md` - `scripts/review/results/*plan-NNN-*` - optional `.planning/quick/*NNN*` 5. Explicitly forbid `docs/plans/README.md`, source files, and tests in the worker prompt. 6. Launch Codex with: `PROMPT=$(< worker.md)` `Codex -p --permission-mode acceptEdits --no-session-persistence --output-format text --max-budget-usd 20 "$PROMPT" </dev/null | tee logs/<worker>.log` 7. Each worker should: - inspect GH + local evidence - draft the canonical plan - run adversarial review - revise once if MAJOR - add `status:plan-review` only if approval-ready - otherwise post blocker comment and leave unlabeled ## Verification rule: check 3 surfaces A worker can advance GitHub state even when artifacts do not appear in the orchestrator's active local worktree. Always verify across these three surfaces: 1. Live GitHub state - issue labels - latest planning comments 2. Local active worktree state - canonical plan path under `docs/plans/` - expected review artifacts under `scripts/review/results/` 3. Remote branch / alternate-worktree provenance - `git ls-remote --heads origin <branch>` - `git show --stat <sha>` - `git show <sha>:path/to/file` ## How to classify outcomes ### Clean success - GitHub label/comment correct - local plan/review artifacts present where expected ### Artifact-placement drift - GitHub `status:plan-review` is correct - worker comments are present - local active worktree is missing claimed artifacts - remote branch commit or sandbox/alternate worktree contains the artifacts Treat this as governance/artifact drift, not as worker failure. Record it explicitly and reconcile before any downstream execution wave. ### Blocked plan - no `status:plan-review` - blocker comment posted - MAJOR findings remain ## Operational lessons - Fresh planning worktrees reduce collisions with a dirty primary checkout. - For planning-only waves, not editing `docs/plans/README.md` is a good collision-avoidance rule. - Worker success messages can overstate local artifact placement; trust live evidence plus git provenance, not the terminal summary alone. - If a worker used a sandbox/in-repo alternate worktree, GitHub may already be correct while the orchestrator's external worktree stays unchanged. ## Morning handoff format Report per issue: - issue number - GitHub status label verified or not - local artifact presence verified or not - remote-branch artifact presence verified or not - disposition: - cleanly ready for approval - ready on GitHub but artifact reconciliation needed - blocked / needs rewrite
Related Skills
digitalmodel-orcawave-orcaflex-proof-workflows
Class-level digitalmodel OrcaWave/OrcaFlex readiness, semantic-proof, fixture-proof, and closeout workflows.
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.
orcawave-orcaflex-readiness-audit
Audit the real readiness of digitalmodel OrcaWave/OrcaFlex spec-driven workflows by reconciling workspace-hub issues, source/tests, semantic-equivalence boundaries, and wiki synthesis gaps.
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
tdd-verification-and-adversarial-review
Verify pre-written TDD tests pass, conduct adversarial code review on committed diffs, and route findings to existing 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
multi-role-agent-contract-review-pipeline
Execute a 4-role agent team (Planner/Architect/Reviewer/Integrator) pipeline for self-reviewing knowledge artifacts before delivery
gsd-adversarial-review-pattern
Catch hidden test failures by running adversarial review on sparse-data edge cases before final push