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 PANYUXIN6/pyx-skills --skill code-reviewgit clone --depth 1 https://github.com/PANYUXIN6/pyx-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/panyuxin6/pyx-skills/code-review)<a href="https://agentmods.dev/skills/panyuxin6/pyx-skills/code-review"><img src="https://agentmods.dev/badge/skills/panyuxin6/pyx-skills/code-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/panyuxin6/pyx-skills/code-review"><img src="https://agentmods.dev/badge/skills/panyuxin6/pyx-skills/code-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 | $0.00103 | $0.03161 |
| Opus 5.5 | $0.00041 | $0.01264 |
| Sonnet 5.5 | $0.00021 | $0.00632 |
| Haiku 4.5 | $0.00010 | $0.00316 |
Grade A, and why
code-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 16d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
代码审查
本技能是代码审查的轻量协调层。Codex 负责理解意图、契约、行为和风险;scripts/review.mjs 负责可机械判定的目标成员、快照、证据坐标、声明的处理状态、质疑覆盖、输入新鲜度和结论一致性。Runner 不派发模型,也不能证明代理理解了项目,或质疑结论在语义上真实、独立;命令成功只能证明冻结输入和已记录的流程状态,不能证明语义完整性或正确性。
在用户另行授权修复前,目标代码、规格和 Git 历史保持只读。除非用户明确选择其他位置,运行时和候选产物只能写到目标仓库外。
调用 Runner 或创建审查产物前,同时需要实现目标和明确审查意图。查找缺陷或风险、评估质量、验证正确性或需求符合性、检查编码或实现标准、执行具名审查维度,或产出 Findings,都满足意图门槛。仅阅读、解释、总结、绘制地图,或追踪架构、数据流、实现行为或实现方法的请求不满足。“inspect”“check”“look at”或“检查一下”等中性动词单独出现也不满足。探索性请求不得调用 Runner 或创建 Finding 产物;使用普通仓库探索或其他直接适用技能。
审查目标必须至少包含一个软件实现产物。散文需求和设计文档只能作为评估实现的权威或上下文。用户要求审查文档自身的清晰度、结构、一致性或设计质量时,本技能和 Runner 不适用。
模型与推理配置
主审和发现质疑统一使用 gpt-6.1-sol,推理程度为 xhigh。只有已确认当前会话同时使用这两项设置时,才在当前会话执行语义审查。
技能文本不能切换宿主会话的模型。当前设置不符或无法确认时,使用 Native spawn_agent,明确传入 model: "gpt-6.1-sol"、reasoning_effort: "xhigh" 和 fork_turns: "none",将完整审查交给一个主审子代理。提供用户请求、目标绝对路径、已确认约束与验收来源、本技能绝对路径;由该代理读取技能并执行后续完整流程。主审子代理以 Native 任务的明确派发参数确认设置,不再为模型设置重复委派主审。宿主依据返回的 Runner 产物核对并交付结果,不重复全面审查。Native 委派或指定模型、推理程度不可用时,说明限制并停止,不静默替换设置。
独立质疑子代理也明确传入上述模型、推理程度和隔离参数;是否需要独立质疑仍按 发现质疑协议 的风险路由决定。
1. 确定权威和目标
阅读约束目标的全部仓库规则,如适用的 AGENTS.md、CLAUDE.md、CONTRIBUTING.md 和编码标准。只加载与变更模块、契约或调用路径有关的架构文档和 ADR。仓库规则和已确认需求优先于本通用基线。
解析被请求目标:
- 当前变更:将
HEAD -> index已暂存变更、index -> worktree未暂存变更及未跟踪文件作为独立项目冻结;绝不可合并为一个HEAD -> worktree净 diff。 - 分支、提交、范围或 PR 对比:只解析一次固定比较点;三点比较使用其合并基点。
- 当前状态功能审查:从入口、调用方、契约、配置和测试中按语义发现完整文件范围,再将其作为显式文件冻结;此模式不需要 Git、diff 或基线。
- 只有归因变更、回归、遗漏或变更集范围结论需要 Git 基线。仓库证据无法识别所请求目标时才询问。
“已修复,再审查”等后续请求,除非用户要求更广范围,否则默认验证原发现、修复变更及受影响调用路径。把已有报告和质疑记录作为证据线索。重新检查先前反证是否仍适用;只有新证据、契约变更或相关代码变更使其失效时,才重新提出已反驳的主张并解释原因。insufficient_evidence 不是反驳。针对当前后续范围准备全新运行;不得把旧锚点、处理状态、质疑结论或批准当作当前验证。报告原发现的当前状态,并让结论仅覆盖实际复查内容;仅验证修复并不批准整个 PR。
工作区使用 node <skill-directory>/scripts/review.mjs prepare --repo <repository>;固定范围增加 --base <ref> --head <ref>;当前状态范围重复使用 --file <path>。读取返回的 queue_path,而非完整 Manifest:队列只含语义审查所需的项目 ID、路径、变更范围、元数据和排除项。冻结源代码相对于队列目录位于 snapshots/<item_id>.before|after;完整完整性数据由 Runner 保留在模型上下文外。
What ships with it
14 files 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.
- references/acceptance-review.md 3.5 KB
- references/architecture-standards.md 1.6 KB
- references/challenges.schema.json 4.1 KB
- references/correctness-quality.md 2.1 KB
- references/finding-challenge.md 4.0 KB
- references/findings.schema.json 2.5 KB
- references/focused-review.md 1.4 KB
- references/removal-plan.md 1.0 KB
- references/review-runtime-protocol.md 7.0 KB
- references/routine-review.md 2.3 KB
- references/security-reliability.md 2.0 KB
- references/spec-compliance.md 1.1 KB
- scripts/review.mjs 60 KB runs code
- scripts/review.test.mjs 38 KB runs code
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.
- 16d ago Changed · +8 lines 2d99795d3b04
- 1mo ago Changed · -110 lines · +23 tokens per session 4c93ac3a0293
- 1mo ago Changed · +17 lines 6ba54d1fb50c
- 2mo ago Changed · -113 tokens per session 5c8cd58a7474
- 2mo ago First seen · 189 lines · 193 tokens per session scan A f992ee9b5ed0
code-review is a skill published in the GitHub repository PANYUXIN6/pyx-skills (8 stars, last pushed 17d ago), licensed MIT. It adds 103 tokens to every session and 3,161 once invoked, about $0.0004 per session on Opus 5.5. 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.
code-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| code-reviewPANYUXIN6/pyx-skills | Skill | 8 | 17d ago | MIT | A | 103 | Claude Code, Codex |
| autoreviewopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 115 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 48 | Claude Code, Codex |
| revdiff-planumputun/revdiff | Skill | 945 | yesterday | MIT | A | 84 | Claude Code |
| explore-unknownsdzhng/skills | Skill | 1.4k | 2d ago | MIT | A | 162 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | 4d ago | MIT | A | 70 | Claude Code |