planning-lane-cross-review-permission-fallback
Handle overnight planning-only lanes where plan revision/editing works but real cross-provider review dispatch is permission-blocked.
Best use case
planning-lane-cross-review-permission-fallback is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Handle overnight planning-only lanes where plan revision/editing works but real cross-provider review dispatch is permission-blocked.
Teams using planning-lane-cross-review-permission-fallback 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/planning-lane-cross-review-permission-fallback/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How planning-lane-cross-review-permission-fallback Compares
| Feature / Agent | planning-lane-cross-review-permission-fallback | 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?
Handle overnight planning-only lanes where plan revision/editing works but real cross-provider review dispatch is permission-blocked.
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
# Planning-lane cross-review permission fallback Use this when a planning-only overnight worker can successfully revise plans but cannot run the repo's real cross-provider review machinery. ## Problem pattern Observed in the 2026-04-21 CI batch for workspace-hub issues #2441, #2443, and #2444: - the worker could revise `docs/plans/...` files - the worker could write `scripts/review/results/...-r3.md` - the worker could post GitHub comments - but permission policy blocked `scripts/review/cross-review.sh` That means the worker can produce review-shaped artifacts, but not actual Codex/Gemini/Codex cross-provider evidence. ## Required response 1. Do NOT pretend the fallback artifacts are real cross-provider review. 2. If you write fallback review artifacts, add explicit provenance language in every artifact. 3. In every issue comment, disclose that the artifacts are single-author adversarial self-review, not dispatched multi-provider review. 4. Keep the issue in `status:plan-review`. 5. Do NOT create `.planning/plan-approved/*` markers. 6. Recommend a follow-up unsandboxed review wave before any move to `status:plan-approved`. ## Minimum provenance language Use wording equivalent to: - "Provenance note: this artifact is a Codex-authored single-author adversarial self-review because `scripts/review/cross-review.sh` was permission-blocked in this session. It is interim signal, not real cross-provider review evidence." ## What counts as acceptable output Acceptable overnight output: - revised plan files - provenance-tagged `-rN.md` review artifacts - issue comments summarizing current blockers and explicitly disclosing the degraded review mode - a ranking of which plans are closest to approval, with the caveat that real cross-provider review is still required Not acceptable: - calling the fallback artifacts "Wave N cross-provider review" without qualification - moving the issue to `status:plan-approved` - telling the user the plan is approval-ready based only on the fallback artifacts ## Reusable operator note If this fallback happens, the next clean step is: ```bash bash scripts/review/cross-review.sh docs/plans/<plan-file>.md all --type plan ``` run from an unsandboxed session with permission to invoke the provider dispatchers. ## Why this matters The fallback self-review can still be useful for tightening plans overnight, but it must not silently downgrade the repo's governance standard. The right pattern is: preserve momentum, disclose provenance, and defer approval until real cross-provider evidence exists.
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.
tdd-verification-and-adversarial-review
Verify pre-written TDD tests pass, conduct adversarial code review on committed diffs, and route findings to existing issues
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
batch-syntax-fix-with-regex-line-based-fallback
Fix repeated syntax errors across many files using regex, then fall back to line-based parsing when regex fails
adversarial-code-review-tdd
Systematic adversarial review pattern to identify breaking assumptions in already-passing test suites
adversarial-code-review-for-committed-diffs
Systematic process for reviewing already-committed code changes to catch type inconsistencies, edge cases, and docstring gaps
adversarial-code-review-and-fix
Systematic pattern for catching design flaws in already-passing code through adversarial review, then fixing them with TDD confirmation.
learned-git-worktree-hook-path-and-real-hook-shape-review
Catch hook-installation and governance bugs that only appear in linked git worktrees or against the real generated hook shape, not simplified test fixtures.
interactive-Codex-to-file-based-fallback
Switch from tmux/interactive Codex to file-based Codex -p execution when interactive runs fail with upstream errors or analysis-only stalls, then verify landing from git/GitHub state.
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.
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.