absolute-path-review-dispatch-guard
Prevent Codex/Gemini adversarial review dispatch failures caused by relative prompt-file paths and background workdir drift.
Best use case
absolute-path-review-dispatch-guard is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Prevent Codex/Gemini adversarial review dispatch failures caused by relative prompt-file paths and background workdir drift.
Teams using absolute-path-review-dispatch-guard 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/absolute-path-review-dispatch-guard/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How absolute-path-review-dispatch-guard Compares
| Feature / Agent | absolute-path-review-dispatch-guard | 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 Codex/Gemini adversarial review dispatch failures caused by relative prompt-file paths and background workdir drift.
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
# Absolute Path Review Dispatch Guard Use this when dispatching adversarial plan/code reviews to Codex or Gemini via `terminal(background=true, pty=true)`. ## Problem A prompt file can exist in the target repo, but the reviewer process still fails with: - `cat: .planning/quick/review-<n>-prompt.md: No such file or directory` This can happen even when: - the file was successfully written, - `find`/`ls` confirms it exists, - and `terminal(workdir=...)` was set correctly. ## Root cause In background PTY runs, Codex/Gemini may start with an effective working directory different from the requested repo `workdir`. A real observed case: - requested workdir: `/mnt/local-analysis/workspace-hub/worldenergydata` - Codex startup banner reported: `/mnt/local-analysis/workspace-hub` So relative prompt references like: - `$(cat .planning/quick/review-342-prompt.md)` can fail because they resolve from the wrong directory. ## Reliable pattern 1. Write the prompt file to a real repo path. 2. Verify it exists with `find` or `ls`. 3. Dispatch reviewers using absolute paths for: - prompt file - tee output file Example: ```bash codex exec "$(cat /mnt/local-analysis/workspace-hub/worldenergydata/.planning/quick/review-342-prompt.md)" \ 2>&1 | tee /mnt/local-analysis/workspace-hub/worldenergydata/.planning/quick/review-342-codex.out gemini exec "$(cat /mnt/local-analysis/workspace-hub/worldenergydata/.planning/quick/review-342-prompt.md)" \ 2>&1 | tee /mnt/local-analysis/workspace-hub/worldenergydata/.planning/quick/review-342-gemini.out ``` ## Verification steps Before waiting on the process: 1. confirm prompt file exists at the absolute path 2. check initial process output for immediate `cat: ... No such file or directory` 3. if that error appears, kill and relaunch with absolute paths 4. do not assume the issue is the file write itself until you verify the reviewer startup workdir/path resolution ## Artifact rule When a provider still fails after dispatch: - save a canonical review artifact anyway - mark verdict as `UNAVAILABLE` if no substantive review was produced - include concrete failure reason and raw log path ## When this skill helps - adversarial plan review waves - adversarial implementation review waves - any Codex/Gemini background CLI dispatch that reads prompt files with `$(cat ...)` ## Anti-pattern Do not use repo-relative prompt paths in background reviewer commands just because `workdir` was set. That assumption is not reliable enough.
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
python-import-path-mismatch-debugging
Diagnose and fix ModuleNotFoundError when a package is installed but imports still fail due to environment/path mismatches
python-import-path-debugging
Diagnose ModuleNotFoundError when a package is installed but still fails to import
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
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.
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.