AICodingFlow: Skill for Claude Code

.github/skills/review-pr-repo/SKILL.md

review-pr-repo is a skill for Claude Code, Codex from Terry-Mao/AICodingFlow. It costs 26 tokens per session (546 once invoked), scanned A, original, MIT.

Repository-specific guidance used alongside a pull-request review workflow. It adds checks for this project's skills, Git helpers, and review automation while following the main review rules.

In plain words
What is it for?
Use it as supporting guidance when reviewing this repository's skills, GitHub Actions, snapshot files, and review automation.
Why use it?
It helps reviews focus on risks particular to the repository, such as unsafe Git operations, unstable review files, or incorrect local skill paths. It is not a standalone review process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

This is Terry-Mao/AICodingFlow's own configuration. It tells Claude Code and Codex how to work on AICodingFlow itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AICodingFlow configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Terry-Mao/AICodingFlow/main/.github/skills/review-pr-repo/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Terry-Mao/AICodingFlow

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for review-pr-repo

README.md
[![agentmods](https://agentmods.dev/badge/skills/terry-mao/aicodingflow/review-pr-repo/github.svg)](https://agentmods.dev/skills/terry-mao/aicodingflow/review-pr-repo)
Your own site
<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.

agentmods 80×15 button for review-pr-repo

Your own site · 80×15
<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>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 546 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash 5b466837ef4a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

.github/skills/review-pr-repo/SKILL.md · 53 lines

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, and review.json stable 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 authoritative docs/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.

Read the full file on GitHub · 53 lines

Changes

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.

  1. 10d ago First seen · 53 lines · 26 tokens per session scan A 5b466837ef4a

Subscribe to this mod's changes

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.