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 instructions/ccoalm/ccl-skills/agents-mdgit clone --depth 1 https://github.com/ccoalm/ccl-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/instructions/ccoalm/ccl-skills/agents-md)<a href="https://agentmods.dev/instructions/ccoalm/ccl-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/ccoalm/ccl-skills/agents-md.svg" alt="Measured on agentmods" 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 | $0.01808 | $0.01808 |
| Opus 5 | $0.00904 | $0.00904 |
| Sonnet 5 | $0.00362 | $0.00362 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
ccl-skills AGENTS.md 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 5d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
本仓把真实研发工作中证明有效的做法提炼为可移植、可验证的 Agent Skills,供 Claude Code、Codex、OpenCode 和其它 Agent Skills 宿主使用。根契约定义全仓共用规则;更近的 AGENTS.md 只补充所在目录的职责、边界和验证要求。
核心产品目标
本仓的产品价值不是让技能文件更完善,而是让 Agent 在真实工作中:
- 质量更高:交付更正确、完整、可维护,减少缺陷和返工。
- 效率更高:用更少的时间、轮次和无效操作完成同等工作。
- 更加自主:在目标和授权范围内完成端到端交付,减少不必要的停顿和人工接力。
- 减少重复劳动:把稳定、重复、可判定的工作交给 Agent,让人专注高价值的目标、判断和创造性工作。
技能、规则、参考材料、脚本、模板、测试和门禁都是实现手段。每次变更必须说明它要改善哪一种真实任务结果;检查通过只证明具体属性,不等于产品价值已经实现。
学习以真实任务的成功结果为锚点,用纠正、失败和返工识别边界,再把可复用机制用于后续同类任务。只有后续结果在质量、效率、自主性或人工介入上得到改善,才能声称能力提升。
自主不等于越权。目标取舍、必要权限、不可逆决定和无法由现有证据判定的终态交给用户;其余安全且在范围内的工作由 Agent 继续完成。
开工契约
- 先读再改:修改前读本文件、目标路径上更近的
AGENTS.md、README.md和docs/CONTRIBUTING.md,再进入对应技能流程。 - 必须隔离:根目录有
.worktree-only。任何修改都必须在非main的独立功能 worktree 中完成;主检出只作干净基线和集成点。 - 先判 owner:技能规则、触发词、流程和复盘沉淀归
skill-extraction-workflow;产品研发流程归product-rd-workflow;bug 和失败证据先走defect-diagnosis;读者文档在实质 owner 定稿后走tighten-doc。 - 共享 Git 面去会话化:commit/merge/squash message、分支名及 PR/MR 的标题、正文、评论和标签不得包含 AI 会话链接或 ID、模型 co-author/session 尾注、生成式落款、会话过程内容或「吸收/借鉴外部实践」类出处措辞。只写中性的能力与变更说明,来源证据留在私有复盘存档;宿主默认尾注不得覆盖本条。
- 提交或推送前,以实际落地目标运行
python3 skills/skill-extraction-workflow/scripts/shared_git_surface_gate.py --repo . --base-ref <target>(feature→dev 用origin/dev,dev→main 用origin/main)。 - 新建或编辑 PR/MR 前,把准确拟用的标题和正文写入 UTF-8 临时文件,再运行
python3 skills/skill-extraction-workflow/scripts/shared_git_surface_gate.py --repo . --base-ref <target> --pr-text-file <proposed-pr.md>。本地命令不读取评论、标签或平台生成的 merge message;这些面另做平台侧回读。
- 提交或推送前,以实际落地目标运行
- 控制范围:只改完成当前目标所需的文件。不要顺带重构、发布、改保护设置或清理无关内容。
契约与技能层级
- 指令从仓库根到当前目录叠加;同主题以更近的契约为准。子契约不得放宽安全、权限、owner 路由、worktree 隔离或验证门禁。
- 门禁覆盖范围由内置源码扩展名和显式
--source-ext共同决定。当前源码类型为.sh、.py、.ts、.mjs、.rb、.go、.dart;新增类型先核对source_exts,缺失时显式传参并记录验证证据。 - 范围内每个直接包含源码的目录必须有非空
AGENTS.md。新增契约至少说明目录职责、局部边界和验证;覆盖门禁只证明文件存在,不证明内容正确。 - 新增或改写
AGENTS.md必须保留独立 review/challenge 结论。修改子契约前核对父级,不复制父级正文。 - 每个技能以
skills/<name>/SKILL.md为入口,长清单、模板和案例放references/。AGENTS.md管仓库执行契约,agent-context/session-start.md管跨宿主路由与安全硬规则。
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.
- 5d ago First seen · 67 lines · 1,808 tokens per session scan A d2e2aa122881
ccl-skills AGENTS.md is an instructions file published in the GitHub repository ccoalm/ccl-skills (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,808 tokens to every session, about $0.0090 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).