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 skills add CCDawn/codex-skills --skill briefbound-pr-reviewgit clone --depth 1 https://github.com/CCDawn/codex-skillsWrote 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/ccdawn/codex-skills/briefbound-pr-review)<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-pr-review"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-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/ccdawn/codex-skills/briefbound-pr-review"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-pr-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00055 | $0.01515 |
| Opus 5 | $0.00028 | $0.00758 |
| Sonnet 5 | $0.00011 | $0.00303 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
briefbound-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 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Briefbound PR Review
目标
只读审阅 PR、diff、branch 或 commit range，判断需求覆盖、回归风险和 merge readiness。先给 findings，不用长矩阵掩盖结论；审阅阶段不顺手改代码。
Briefbound task contract
- Context Boundary: PR/diff/base-head、需求来源、验证证据、禁止编辑边界、集成目标和排除范围。
- Output Contract: risk-ranked findings、简洁结论、证据缺口、修复顺序或 merge route。
- Allowed Action: 读取 diff/上下文并运行安全检查；不编辑、移动 HEAD/index、合并、推送或发布。
- Success Evidence: diff 与需求已对照，关键证据已检查，每条 finding 绑定位置、影响和验证条件。
- Stop Condition: 缺可审对象、审查目标/需求无法推断、关键证据不可得、对象漂移或远程/高风险动作未授权。
- Route Out: 对应开发 owner、
briefbound-bug-review、briefbound-performance-engineering、briefbound-planning、briefbound-router、提交/PR/合并准备或 BLOCKED。
统一调用契约
只处理 Briefbound task contract 范围；不匹配时回 briefbound-router 或更具体 owner。用户可见内容默认中文，只报结论、证据、风险和产出；Route Out 仅以 Briefbound task contract 为准，末行写 下一步建议: <一个具体动作>。
审阅流程
- 定位 PR、base/head、merge-base 和实际 diff；检查工作区/分支是否漂移。
- 从用户要求、PR body、issue/spec、现有行为和项目规则中取得需求来源；关键验收项标注
COVERED / PARTIAL / UNVERIFIED / OUT_OF_SCOPE，PARTIAL/UNVERIFIED必须进入 finding 或证据缺口。只有高影响目标无法推断时才回 Briefbound Router 对齐。 - 阅读变更及必要上下文，核对状态/API/数据/配置/迁移/用户流程和保护边界。
- 检查最新测试、构建、lint、类型、运行时或手工验收；按
CODE / LOCAL_CHECKS / LOCAL_RUNTIME / PACKAGED / REMOTE分别记录实际证据，不跨层推断。 - 按 diff 风险选择相关视角，不固定遍历完整清单；只输出由本次变更引入、暴露或会阻塞集成的问题。性能视角只在热路径、规模、查询/I/O、缓存/队列、并发、包体或既有性能契约被触及时启用。
- findings 优先，再给 merge 结论和 route。
效率标注 FAST / CHECK / PROFILE：FAST 无需新增验证，CHECK 用结构或确定性计数，PROFILE 需要测量；只为后两类展开。
明显 N+1、循环 I/O、重复全量计算或无界资源增长可用结构/确定性计数形成 finding；声称“更快/回归”必须有可比较 baseline。需要实际 profiling 或 before/after 时以本 skill 为 primary、briefbound-performance-engineering 为 support，不把每个 PR 变成性能审计。
范围内的可操作 review feedback 标注 OPEN / ADDRESSED / VERIFIED / DEFERRED；回复或改动仅到 ADDRESSED，复验才到 VERIFIED。未关闭的 requested change 阻止 READY；advisory 延后写原因和 owner。
Findings
P0 BLOCKER：数据丢失、安全事故、核心不可用或不可逆发布风险。P1 MUST_FIX：重要需求缺失、明确 bug、关键契约/测试/迁移风险。P2 SHOULD_FIX：边界、错误处理、维护性或局部回归风险。P3 NICE_TO_HAVE：默认省略；只有能明显降低近期误改或审阅成本时才保留。
每条包含位置、问题、影响、建议和验证条件。纯风格、无行为影响的命名或未被 diff 影响的既有问题不算 finding。没有问题时明确“未发现阻塞性问题”及证据边界。
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.
- 10d ago First seen · 80 lines · 55 tokens per session scan A 83f3e6257ca5
briefbound-pr-review is a skill published in the GitHub repository CCDawn/codex-skills (5 stars, last pushed 28d ago), licensed MIT. It adds 55 tokens to every session and 1,515 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
chinese-code-review
A Chinese-language code-review communication guide with templates and severity levels for review comments.
receiving-code-review
A guide for handling code-review feedback carefully. Code review is the process of checking proposed changes before they are accepted into a project.
requesting-code-review
A code-review procedure for checking completed work against its requirements before it spreads or is merged. A code reviewer is a person or agent who looks for defects and missing parts.
legacy-safe-edit
A set of practices for changing existing or old codebases safely. It focuses on finding dependencies, following local coding conventions, and making small changes that can be checked and reverted.
security-review
A code-security review guide covering common risks such as injection, weak login protection, unauthorized access, and sensitive-data exposure. It is written in Chinese and includes rules and examples for safer code.
code-review-self
A self-review checklist for checking code before committing it or opening a pull request, which is a request for teammates to review proposed changes.