Borrowing it
Nothing to install: this file belongs to shanggqm/codexU. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shanggqm/codexU/main/.agents/skills/codexu-pr-review/SKILL.mdgit clone --depth 1 https://github.com/shanggqm/codexUWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/shanggqm/codexu/codexu-pr-review)<a href="https://agentmods.dev/skills/shanggqm/codexu/codexu-pr-review"><img src="https://agentmods.dev/badge/skills/shanggqm/codexu/codexu-pr-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shanggqm/codexu/codexu-pr-review"><img src="https://agentmods.dev/badge/skills/shanggqm/codexu/codexu-pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00079 | $0.00747 |
| Opus 5 | $0.00039 | $0.00374 |
| Sonnet 5 | $0.00016 | $0.00149 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
codexu-pr-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codexU PR Review
Use this skill only inside the codexU repository. Review by default; do not edit the branch, post comments, approve, merge, or close a PR unless the user asks.
Establish The Baseline
- Read
AGENTS.mdcompletely. - Read the documents relevant to the diff:
- Product:
README.md, the matchingdocs/PRD-*.md, andCHANGELOG.md. - UI:
docs/DESIGN_SYSTEM.md. - Privacy or network:
SECURITY.md. - Packaging or compatibility:
DISTRIBUTION.mdandMakefile. - Contributions:
CONTRIBUTING.md,.github/pull_request_template.md, and CI.
- Product:
- Inspect
git status, the base/head relationship, the complete diff, changed files, commits, and test evidence. Preserve unrelated working-tree changes. - For a GitHub PR, inspect its current description, reviews, checks, and
discussion with
ghwhen available. - Separate documented requirements from roadmap inference. Do not present an experimental branch, open PR, or issue as an accepted commitment.
Apply The Product North Star
codexU is a local-first, privacy-preserving, lightweight macOS menu-bar and desktop tool for quickly judging AI coding quota, usage, trends, and task state. Prefer changes that make those judgments more accurate, faster, quieter, or more reliable. Treat general system monitoring, agent orchestration, remote control, marketing surfaces, and personal workflow replacements as outside the default product boundary.
Review In Order
- Check the hard gates in
references/acceptance-rubric.md. Any unresolved hard-gate failure blocks merge regardless of score or CI status. - Verify that the user problem is concrete, frequent enough for the upstream product, and solved without unnecessary controls or information density.
- Check that the implementation extends shared domain/provider/presentation models instead of adding provider-, palette-, or mode-specific branches.
- Verify data semantics: official, local, fallback, estimate, missing, stale, and zero must remain distinguishable.
- Verify UI consistency, accessibility, stable layout, and idle resource use.
- Check failure paths, compatibility, migrations, documentation, and tests in proportion to risk.
- Apply the weighted rubric only after the hard gates pass.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 66 lines · 79 tokens per session scan A d16cc4862429
codexu-pr-review is a skill published in the GitHub repository shanggqm/codexU (344 stars, last pushed 9d ago), licensed MIT. It adds 79 tokens to every session and 747 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
handoff
Transfer the current coding, debugging, planning, or architecture session to AI Badger. Use for broad session continuation; use badger-review for an independent review.
badger-review
Prepare current-session guidance for an independent AI Badger review of recent repository work. Use only when the user wants a Badger review, not for generic review requests or session continuation.
tfx-prune
A cleanup workflow that asks three AI coding assistants to independently identify unnecessary code, then removes only issues they agree are unwanted. It checks for duplication, needless abstractions, excessive error handling, and similar readability problems.
tfx-review
A code-review workflow that asks several command-line AI reviewers to inspect changes independently, then reports issues that at least two reviewers agree on. TDD means test-driven development, where tests are written to guide implementation, but this add-on is for reviewing code rather than defining TDD.
tfx-analysis
A code and architecture analysis workflow that can ask several command-line agents to examine a project from different viewpoints, including architecture, security, performance, user experience, and documentation.