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 kakadeka/Baton --skill baton-lean-reviewgit clone --depth 1 https://github.com/kakadeka/BatonWrote 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/kakadeka/baton/baton-lean-review)<a href="https://agentmods.dev/skills/kakadeka/baton/baton-lean-review"><img src="https://agentmods.dev/badge/skills/kakadeka/baton/baton-lean-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/kakadeka/baton/baton-lean-review"><img src="https://agentmods.dev/badge/skills/kakadeka/baton/baton-lean-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 | $0.00058 | $0.00730 |
| Opus 5 | $0.00029 | $0.00365 |
| Sonnet 5 | $0.00012 | $0.00146 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
baton-lean-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.
What it actually says
baton-lean-review（只读精简审查）
审查当前 diff 或指定范围，按净收益排序输出报告。本 skill 绝不修改代码；不替代正确性/安全/Fidelity Reviewer。
优先级（不可违反）
用户明确要求/FROZEN > 安全与数据完整性 > Contract/DoD/Fidelity > 正确性 > 记忆闭环 > 精简目标 > 输出风格。
决策阶梯（按顺序停止在第一个可行层级）
- 这项需求是否真实需要？推测性未来需求先不做。
- 仓库是否已有 helper/类型/模式/组件？优先复用。
- 标准库是否覆盖？
- OS/浏览器/数据库/框架原生能力是否覆盖？
- 已安装依赖是否覆盖？
- 能否通过删除、配置或组合现有能力完成？
- 前六项都不成立，才新增最小实现。
标签
| 标签 | 含义 |
|---|---|
delete |
死代码、投机功能 |
reuse |
仓库已有能力可复用 |
stdlib |
手写标准库已有等价物 |
native |
平台原生能力可替代 |
yagni |
单实现接口、单产品工厂、无人使用配置 |
shrink |
逻辑等价但可更小 |
keep |
安全/正确性/兼容性强制保留 |
输出格式
文件:行号 | 标签 | 建议 | 替代物 | 风险门禁 | 预计净变化
keep标签必须说明保留原因（安全/正确性/兼容性）。- 涉及安全校验、防数据丢失、凭据处理、FROZEN/Fidelity 的代码默认 keep，除非有更强证据。
- 每条建议给出可验证的替代方案；没有替代方案的不建议。
边界
- 只读：不修改任何文件、不提交、不 push。
- 不替代正确性/安全/Fidelity Reviewer。
- 报告末尾标注：审查范围、审查身份（无法确认写 unknown）、未覆盖部分。
从主 SKILL 迁入的 Lean Gate 精华
主 SKILL 不再携带 Lean Gate。需要精简审查时显式使用本 skill（默认安装不含本文件）。
优先级永远：用户明确要求/FROZEN > 安全与数据完整性 > Contract/DoD/Fidelity > 正确性 > 记忆闭环 > 精简目标 > 输出风格。
不可精简项：信任边界输入校验；防数据丢失的错误处理；鉴权/授权/凭据/注入防护；无障碍基础；用户明确要求与 FROZEN/Fidelity；DoD 与非平凡逻辑的最小可运行检查。
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 · 59 lines · 58 tokens per session scan A c1fc9c8fa5d2
baton-lean-review is a skill published in the GitHub repository kakadeka/Baton (4 stars, last pushed 10d ago), licensed Apache-2.0. It adds 58 tokens to every session and 730 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
context
CONTEXT: Cognitive Order Normalized in Transformer EXtract Truncated. Cross-model context handoff via Progressive Density Layering, MLDoE expert compression, Japanese semantic density, and Negentropic Coherence Lattice validation. Creates portable carry-packets that transfer cognitive state between AI sessions. Use…
code
Review code through the lens of a senior engineer.
verification
Verify agent code against organizational policies and best practices. Trigger this skill when the user says something like "verify my agent", "review agent code", "check compliance", "audit my agent", "check my agent against rules", or "validate agent implementation".
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
review
Review code changes for security, performance, bugs, and quality. Reviews staged changes, unstaged changes, specific commits, or PR-ready diffs.
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.