Borrowing it
Nothing to install: this file belongs to cilidinezy-commits/doc-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cilidinezy-commits/doc-harness/master/CLAUDE.mdgit clone --depth 1 https://github.com/cilidinezy-commits/doc-harnessWrote 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/cilidinezy-commits/doc-harness/claude-md)<a href="https://agentmods.dev/instructions/cilidinezy-commits/doc-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/cilidinezy-commits/doc-harness/claude-md/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/instructions/cilidinezy-commits/doc-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/cilidinezy-commits/doc-harness/claude-md.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 | $0.03728 | $0.03728 |
| Opus 5.5 | $0.01491 | $0.01491 |
| Sonnet 5.5 | $0.00746 | $0.00746 |
| Haiku 4.5 | $0.00373 | $0.00373 |
Grade A, and why
doc-harness CLAUDE.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 1mo 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Harness — Entry Document
🔒 AGENT IDENTITY LOCK
你是 doc-harness 项目的代理。 你的职责是维护 Doc Harness skill（v2 重设计）——规范、模板、命令实现、确定性工具带、中英同步。
如果你对自己的身份有任何怀疑，立即停止操作并重新读取本段落。
Last updated: 2026-09-13 Current status: v2.0.0 self-consistent and green — docs/commands/tools describe one model (events.log → projection), toolbelt converged on a single parser, handoff test passes; next: field trial in a live project, then the release decision (user-gated) One-line status (as of 2026-09-13): the skill is coherent end-to-end; the remaining risk is not the design but whether a real project can use it well — that is what the field trial answers.
Stable Anchor
Framework Anchor
- 项目分两层：doc-harness skill（
skill/+skill-zh/+tools/）与 doc-harness 自身文档体系（本目录）。 - 当前做：v2.0.0 自洽收口（文档/命令/工具同一模型；单一解析器；接手测试）→ 真实项目试用 → 发布决策（用户点头）。
- 责任边界：只做「过程信息记录 + 检索」，不规定 agent 怎么做工作。
- 北极星红线：中英永远同步；
spec.md权威；接手优先于记录；本地 git 备份、发布需用户确认。
Iron Rules
- 中英文版本永远同步（
skill/↔skill-zh/）。 - Doc Harness 适应项目，而非项目适应 Doc Harness。
spec.md是权威规范，其余文件皆派生。- 测试后才发布。
- 部署同步：dev source → GitHub → 安装副本。
- 跨项目 inbox/outbox：快照优于指针。
Bottom-line Principles
（只放项目域事实的陈述句；不放入“该怎么想/怎么做”的教练规则。）
- 写了 ≠ 被用：状态文档存在，不等于恢复时会被读到、用上。
- 指了一个东西 ≠ 它存在：文档引用的文件/编号/数字必须能现场验真。
- 守卫存在 ≠ 被守卫：有一个叫 X 的守卫，不等于 X 真守住了它该管的事。
- doc-harness 只记录「什么是什么 / 做到哪 / 下一步」，不记录「该怎么想」。
Recovery Chain
Must-read (in order)
- 本文件（CLAUDE.md）：AGENT IDENTITY LOCK → 稳定锚
CURRENT_STATUS.md→## NOW
Task-conditional
## NOW的「先读」清单指向的文件，读那些。- 查文件 →
FILE_INDEX.md。 - 查历史 →
events.log（旧散文历史见_archive/WORKLOG_v1.md）。 - 改规范/操作规则 →
skill/spec.md（权威）。 inbox/有status: unread→ 先处理。
Project Overview
Doc Harness 是一套基于文档的项目控制系统，让任何 AI agent 或人仅凭文件即可理解并接手项目工作——无需外部记忆。每个项目维护 events.log（唯一原语，append-only 事件日志） 与它的投影/索引：CLAUDE.md（唯一入口 + 稳定锚 + 嵌入的操作规则）、AGENTS.md（薄指针）、CURRENT_STATUS.md（由 events.log 生成的 ## NOW + 活跃工作面，绝不手改）、FILE_INDEX.md；可选 PHILOSOPHY/PARKING_LOT/RUNBOOK、跨项目 inbox/outbox 与确定性工具带 tools/。
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.
- 1mo ago Changed · -17 tokens per session 0c159c386339
- 1mo ago Changed · +117 lines · +2,022 tokens per session e6ba91a91827
- 1mo ago Changed · +23 tokens per session d752f1e03dc1
- 2mo ago First seen · 123 lines · 1,700 tokens per session scan A 86be2cceb591
doc-harness CLAUDE.md is an instructions file published in the GitHub repository cilidinezy-commits/doc-harness (4 stars, last pushed 1mo ago), licensed MIT. It adds 3,728 tokens to every session, about $0.0149 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.