Borrowing it
Nothing to install: this file belongs to Terry-Mao/AICodingFlow. 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/Terry-Mao/AICodingFlow/main/.github/skills/review-pr-repo/SKILL.mdgit clone --depth 1 https://github.com/Terry-Mao/AICodingFlowWrote 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/terry-mao/aicodingflow/review-pr-repo)<a href="https://agentmods.dev/skills/terry-mao/aicodingflow/review-pr-repo"><img src="https://agentmods.dev/badge/skills/terry-mao/aicodingflow/review-pr-repo/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/terry-mao/aicodingflow/review-pr-repo"><img src="https://agentmods.dev/badge/skills/terry-mao/aicodingflow/review-pr-repo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 49 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Agent Snooping · line 13 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00026 | $0.00546 |
| Opus 5 | $0.00013 | $0.00273 |
| Sonnet 5 | $0.00005 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
review-pr-repo 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 10d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-pr-repo
This file is a companion to the core review-pr skill and
.agents/contracts/review.md.
Do not invoke this file as the primary review entrypoint. The primary entrypoint
is .github/skills/review-pr/SKILL.md; that skill reads this companion when it
needs repository-specific review guidance.
This companion may add repository-specific checks and preferences, but it must not override the core workflow, shared review contract, output schema, severity labels, diff-line targeting, validation rules, or safety rules.
Repository Review Focus
Prioritize findings that affect this repository's skills and PR-review automation:
- Skill files must be concise, operational, and safe for Codex to execute.
- Git helpers must avoid destructive operations, broad staging, unsafe force pushes, and accidental edits to user work.
- GitHub Actions review code must keep
pr_description.txt,pr_diff.txt, andreview.jsonstable and reproducible. - Review automation must not call
gh, post comments, fetch live PR state, or regenerate snapshots while the review skill is running. - Local/shared skill paths must use
.agents/skills/...; GitHub workflow-only skill paths must use.github/skills/.... - Before flagging a referenced path as missing, account for files or directories added, deleted, or renamed within the same PR diff; workflow prompts may point at the post-merge path introduced by that PR.
- Documentation examples must match the actual repository layout and commands.
- When
docs/product/wiki/compiled content changes durable product or workflow facts, verify the authoritativedocs/product/raw/source in the same PR supports the new fact; do not require raw changes for wiki-only recompiles that merely reflect already-updated raw sources. - Validators and report checks that parse
#<number>references should distinguish issue references from PR/source references and enforce issue URL requirements only in an explicit issue or related-issue context. - When multiple changed lines show the same root cause, prefer one actionable finding at the clearest line and mention the broader scope there.
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.
- 10d ago First seen · 53 lines · 26 tokens per session scan A 5b466837ef4a
review-pr-repo is a skill published in the GitHub repository Terry-Mao/AICodingFlow (165 stars, last pushed 12d ago), licensed MIT. It adds 26 tokens to every session and 546 once invoked, about $0.0001 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…