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 agentmods add skills/cedriccmh/claude-auto-patch/create-patchnpx skills add Cedriccmh/claude-auto-patch --skill create-patchgit clone --depth 1 https://github.com/Cedriccmh/claude-auto-patchWhat 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 | $0.00101 | $0.01209 |
| Opus 5 | $0.00051 | $0.00605 |
| Sonnet 5 | $0.00020 | $0.00242 |
| Haiku 4.5 | $0.00010 | $0.00121 |
Grade A, and why
create-patch 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 2d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
为 Claude Code 创建补丁
为 Claude Code 的 minified JS 代码(bun 二进制或 npm cli.js)创建等长二进制补丁。
工作流程
1. 定位 npm cli.js
查找 npm 全局安装的 @anthropic-ai/claude-code 包用于分析(npm 版是文本文件,适合代码探索)。
npm root -g --> <root>/node_modules/@anthropic-ai/claude-code/cli.js
如果未找到,向用户询问:
npm 版 Claude Code 未安装,分析代码需要它作为参考。是否执行
npm install -g @anthropic-ai/claude-code来安装?
确认 cli.js 可用后再继续。
2. 搜索目标代码
运行 scripts/search_target.py 查找相关代码片段:
python scripts/search_target.py <cli.js路径> "<关键词>"
脚本返回匹配的代码片段及其字节偏移和上下文。
如果用户描述模糊,搜索多个相关关键词。常见搜索策略:
- 域名限制:搜索域名字符串(如
api.anthropic.com) - Feature flags:搜索 flag 名称
- 错误消息:搜索错误文本
- API 调用:搜索 endpoint 路径
3. 分析代码
搜索到的片段是 minified JS。需要心理展开还原:
# Minified
return["api.anthropic.com"].includes(Xe)}catch{return!1}
# 展开后
try {
return ["api.anthropic.com"].includes(Xe);
} catch {
return !1; // false
}
对于复杂片段,可以创建格式化副本进行深入分析:
npx prettier --write <临时副本.js>
需要识别:
- 代码做了什么(正在执行的检查/限制)
- 期望的行为是什么(补丁应该把它改成什么)
- 最小替换方案(实现目标的最简替换)
4. 设计等长替换
关键约束:替换后的字节长度必须与原始代码完全一致。
用 JS 注释(/* */)吸收多余字节:
原始: return["api.anthropic.com"].includes(Xe)}catch{return!1}
补丁: return!0/* */}catch{return!0}
^--- 同样长度,合法 JS,不同行为 ---^
运行 scripts/validate_patch.py 验证:
python scripts/validate_patch.py \
--target-re 'return\["api\.anthropic\.com"\]\.includes\([A-Za-z_$][A-Za-z0-9_$]*\)\}catch\{return!1\}' \
--patched-re 'return!0/\* *\*/\}catch\{return!0\}' \
--replacement-prefix 'return!0/*' \
--replacement-suffix '*/}catch{return!0}' \
--file "<cli.js 路径>"
脚本检查:正则是否匹配、长度是否一致、替换是否有效。
5. 注册补丁
读取项目的 auto_patch.py,在 PATCHES 字典中添加新的 PatchDef 条目:
"patch_name": PatchDef(
name="patch_name",
description="补丁说明",
target_re=re.compile(rb'...'),
patched_re=re.compile(rb'...'),
build_replacement=lambda m: _equal_length_replace(
b"prefix", b"suffix", m
),
),
更新 auto-patch-config.json,添加新补丁(默认启用):
What ships with it
3 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.
- 2d ago First seen · 145 lines · 101 tokens per session scan A 589323e98e1e
create-patch is a skill published in the GitHub repository Cedriccmh/claude-auto-patch (11 stars, last pushed 5mo ago), licensed MIT. It adds 101 tokens to every session and 1,209 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…