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-doctorgit 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-doctor)<a href="https://agentmods.dev/skills/kakadeka/baton/baton-doctor"><img src="https://agentmods.dev/badge/skills/kakadeka/baton/baton-doctor/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-doctor"><img src="https://agentmods.dev/badge/skills/kakadeka/baton/baton-doctor.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 | $0.00065 | $0.01046 |
| Opus 5 | $0.00032 | $0.00523 |
| Sonnet 5 | $0.00013 | $0.00209 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
baton-doctor 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 6d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
baton-doctor(只读健康诊断)
检查清单
- 版本事实分层:先判断当前目录是否为 Baton 框架源码仓库(
package.json.name=@kakadeka/baton)。若是,源码版本只取本地package.json.version+ 本地 HEAD;框架仓库的skills/是 canonical 源目录,不把其中的baton-lean-review/baton-debt当业务项目残留。npm latest 与公开库 SHA/tag 只列为发布面证据,不得与私有源码 HEAD 混称新旧。普通业务项目看已跟踪的.baton/config.json、.baton/manifest.json、项目 Skill 与docs/ai_memory/;不再把缺失.baton/version.json当故障。 - Skill 漂移:canonical
skills/baton/SKILL.md与三端镜像逐字节一致?项目内可用node scripts/check-drift.mjs(有脚本时)。默认安装只有baton+baton-doctor;baton-lean-review/baton-debt仅框架仓保留。 - 项目 manifest(仅普通业务项目):
.baton/manifest.json必须存在、是可解析 JSON,且managed至少包含当前默认九项:.cursor/rules/baton.mdc、.baton/runtime/baton-closeout.mjs、.baton/runtime/baton-public-update.mjs,以及.agents/.claude/.cursor/skills/{baton,baton-doctor}/SKILL.md六个项目镜像。逐项读取并用 SHA256 与 manifest 比对;缺失、不可解析、缺项、文件缺失或 hash 不一致都只报告 FAIL,不删除、不修复。项目中的baton-lean-review/baton-debt若存在且未被 manifest 管理,报告为旧默认残留;框架源码的 canonicalskills/目录不适用此条。 - 骨架完整:
docs/ai_memory/关键文件存在且含【归档分卷索引】+【修订记录】;.baton/config.json可解析;.cursor/rules/baton.mdc与三端 Skill 镜像存在且受 manifest 管理。核对主 Skill 含自动语义分卷与即时自动记忆规则。 - Git 状态:分支/HEAD/工作区干净/远端同步(
git fetch只读检查 ahead/behind;不做任何写入)。 - 单写入者锁:
git show-ref refs/baton/ownership-lock是否存在、state.ownership 状态。 - 发布面(框架仓库场景):公开库 CI 最近 run、npm latest 与 tag 对齐。
- 凭据红线自检:最近 diff 与待提交文件扫描——报告命中清单,绝不显示命中正文。
- Codex Windows ACL 兼容:仅当
.agentsOwner 命中CodexSandboxOffline/CodexSandbox或关键 ACE 异常时报告 FAIL。Doctor 不改 Owner/ACE。
输出格式
## Baton doctor 报告 <时间>
- 版本:源码 vX @ <本地HEAD> / npm vZ / 公开 tag+SHA(分别报告,禁止混称)
- Skill:四份一致 / 漂移点名;默认安装=baton+doctor
- 骨架:完整 / 缺失清单
- Git:分支 / HEAD / 干净 / ahead/behind
- 锁:holding(<owner 前 8 位>) / released / 无 ref
- 发布面:CI 最近 <成功/失败> / tag 对齐
- 凭据:命中 N 处(只列文件名)/ 零命中
- Codex Windows ACL:正常 / FAIL
- 建议:<唯一下一步>
边界
- 只读:不修改、不 commit、不 push、不抢锁。
- 诊断结论标注证据来源(命令 → 结果);无法验证的写「未验证」,不得 PASS。
- 修复必须回到 Baton 正常口令(更新 Baton / init);doctor 不越权执行。
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.
- 6d ago Changed a101a179766f
- 10d ago First seen · 40 lines · 65 tokens per session scan A 741ebb814a1c
baton-doctor is a skill published in the GitHub repository kakadeka/Baton (4 stars, last pushed 10d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,046 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…
diagnose
A step-by-step debugging guide for investigating bugs, regressions, and unexpected behavior in software.
gsd-debug
Systematic debugging with persistent state across context resets.
spark-engineer
Use when writing Spark jobs, debugging performance issues, or configuring cluster settings for Apache Spark applications, distributed data processing pipelines, or big data workloads. Invoke to write DataFrame transformations, optimize Spark SQL queries, implement RDD pipelines, tune shuffle operations, configure…
debugging-wizard
Parses error messages, traces execution flow through stack traces, correlates log entries to identify failure points, and applies systematic hypothesis-driven methodology to isolate and resolve bugs. Use when investigating errors, analyzing stack traces, finding root causes of unexpected behavior, troubleshooting…
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.