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 hxy91819/mason-skills --skill autoreviewgit clone --depth 1 https://github.com/hxy91819/mason-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/hxy91819/mason-skills/autoreview)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/autoreview"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/autoreview/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/hxy91819/mason-skills/autoreview"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/autoreview.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 | $0.00106 | $0.00948 |
| Opus 5.5 | $0.00042 | $0.00379 |
| Sonnet 5.5 | $0.00021 | $0.00190 |
| Haiku 4.5 | $0.00011 | $0.00095 |
Grade A, and why
autoreview 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 today.
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.
This is a copy
86% identical to autoreview — 42 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Auto Review
按 description 的条件自动调用，也可显式调用 $autoreview。必须先按名称加载 $bb-model-routing；其路由配置是 reviewer 的 provider、模型、推理级别与 fallback 的唯一来源。依赖不可用时报告缺失，不改用本机 CLI 或宿主 subagent。
派发审查
若当前线程是被派发的执行子线程，且父线程已在任务契约中写明“由父线程统一派发独立审查/验收”，则本线程只运行确定性测试与自检，不重复嵌套启动本技能。
派发前跑完仓库已有的测试、类型检查和 validator 并修到通过，改动定稿后再派发；这些确定性检查能发现的问题不留给审查。
确定准确的审查目标：未提交改动、分支相对指定 base 的差异，或指定 commit；同时整理原始需求和验收条件。读取审查提示词，把其中完整的审查标准、输出格式与本次具体范围一起写入 --task。按已加载的 $bb-model-routing「判断与调用」归类，不在这里另定下限，也不强制 medium 起步。需求与验收条件已明确的审查（含闭合改动、修复后增量、跨模块状态机的深度审查）使用 simple；只有该标准里的 medium 三类（含并发、锁与崩溃恢复、租户或安全隔离、发布签字、唯一审查人）才升档：
bb-dispatch --difficulty simple --task '<仓库、Git 审查范围、原始需求、验收条件，以及 references/review-prompt.md 的完整审查标准和输出格式>'
将占位文本换成实际路径、ref、需求和提示词内容；不要只把提示词文件路径交给 reviewer，因为派发环境可能无法读取该文件。模型或推理级别不写入 --task；目标环境和失败续派按 $bb-model-routing 的规则处理。向用户报告线程 ID、实际选择和状态；通过 BB 完成通知接收结果。创建线程不等于审查完成。
核实与收尾
主 Agent 逐条核实发现，阅读相关代码与必要的依赖契约。接受当前任务范围内真实、可操作的缺陷；说明拒绝项理由。修复后运行相关验证。修复只是对首轮发现的局部改动且有回归测试时，主 Agent 自行核实；修复引入新行为或超出原发现范围时，再对新差异派发一次增量复审（同一交付任务内独立审查最多 2 轮：首轮审查 + 一次修复后复审；修复后复审边界已闭合时用 simple）。第 2 轮复审后若无新的 P0/P1，或仅剩主 Agent 可直接核实的小修，主 Agent 自行修完并验证通过即可收尾，不再继续循环派发第 3 轮及以上的审查线程。超出原任务的产品或接口决策交给用户决定。
最终报告列出审查范围、线程 ID、验证结果，以及发现的处理结果。每个审查线程处理完后回写裁决并归档：
bb-dispatch --record-decision <线程ID> --decision accepted|rejected
bb thread archive <线程ID>
归档后仍可用 bb thread show <线程ID> 回看单次审查记录，用 bb-dispatch --history-summary 查看跨线程统计。
What ships with it
4 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.
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.
- today Changed 82563594a1a7
- 19d ago Changed 5cf100ce550a
- 22d ago Changed · +9 lines · +40 tokens per session db4e84d01456
- 23d ago Changed 0bb7dd3d86ee
- 24d ago Changed · +2 lines 02536e902956
- 1mo ago Changed · -3 lines · +42 tokens per session 239ce89adb95
- 1mo ago Changed · -530 lines · -6 tokens per session 5db152a5e0fb
- 1mo ago Changed · -70 lines 7f22aa08553c
- 1mo ago Changed · +45 lines f9a82aa84090
- 1mo ago First seen · 583 lines · 30 tokens per session scan A 76f8fb5d763e
autoreview is a skill published in the GitHub repository hxy91819/mason-skills (3 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 948 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to autoreview, differing in 42 lines, and is treated as a copy.
autoreview compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| autoreviewhxy91819/mason-skills | Skill | 3 | today | MIT | A | 106 | Codex |
| autoreviewopenclaw/clawhub | Skill | 9.5k | today | MIT | A | 17 | Claude Code, Codex |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 2d 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 | 947 | 3d ago | MIT | A | 84 | Claude Code |
| explore-unknownsdzhng/skills | Skill | 1.4k | yesterday | MIT | A | 162 | Claude Code, Codex |
| re0-mergeLilMGenius/paperthin | Skill | 1.4k | today | MIT | A | 70 | Claude Code |