Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/0xranx/agentbrief/review-processnpx skills add 0xranx/agentbrief --skill review-processgit clone --depth 1 https://github.com/0xranx/agentbriefWrote 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/0xranx/agentbrief/review-process)<a href="https://agentmods.dev/skills/0xranx/agentbrief/review-process"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/review-process.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00012 | $0.00348 |
| Opus 5 | $0.00006 | $0.00174 |
| Sonnet 5 | $0.00002 | $0.00070 |
| Haiku 4.5 | $0.00001 | $0.00035 |
Grade A, and why
review-process 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 5d 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.
What it actually says
Code Review Process
Step-by-Step Review Workflow
1. Understand Context
- Read the PR description and linked issues
- Understand what problem is being solved and why
- Check if the approach was discussed beforehand (design doc, RFC, issue thread)
2. High-Level Pass
- Look at the file list -- does the scope make sense for the stated goal?
- Check for unrelated changes mixed in (should be separate PRs)
- Review the overall architecture: does the approach fit the codebase patterns?
3. Detailed Review
- Walk through the code in logical order (not file order)
- Start from the entry point and follow the data flow
- For each change, evaluate against the review dimensions (correctness, architecture, naming, tests, errors, security)
- Note findings with severity, location, issue, and suggestion
4. Test Review
- Are the right things being tested?
- Do tests cover both happy path and error paths?
- Are tests testing behavior (what), not implementation (how)?
- Would the tests catch a regression if someone changed the implementation?
5. Synthesize Feedback
- Group findings by severity
- Lead with critical issues
- Provide an overall summary: approve, request changes, or comment
- If requesting changes, be clear about what is blocking vs. what is optional
6. Follow-Up
- Re-review addressed feedback promptly
- Verify fixes actually resolve the issue (not just superficially)
- Approve once blocking issues are resolved -- do not add new non-blocking feedback on re-review
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.
- 5d ago First seen · 42 lines · 12 tokens per session scan A daf30bad1931
review-process is a skill published in the GitHub repository 0xranx/agentbrief (45 stars, last pushed 5mo ago), licensed MIT. It adds 12 tokens to every session and 348 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
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
ai-style
当任务是用中文撰写或改写面向读者的文案（产品发布稿、公众号文章、邮件、README 等）， 或用户反馈文字「AI 味太重」「不像人写的」时，加载本 Skill。.
curly-quote-sft
Skill "curly-quote-sft" from bojieli/ai-agent-book, covering 中文技术文档符号与引用规范, 何时加载, 符号定义, 决策优先级 and 正反例约束.
triage
你是当前任务的分诊协调者。先识别用户的全部目标、顺序依赖和验收条件，再按 “事实检索 → 计算/执行 → 写作”顺序逐步请求切换到需要的专业能力。不要替专业 能力完成它的工作，也不要在信息缺失时臆造结果。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
research
用真实检索工具查找可追溯的事实、数据和来源。.