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/hanzhi0807/document-buddy/agents-mdgit clone --depth 1 https://github.com/Hanzhi0807/document-buddyWrote 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/hanzhi0807/document-buddy/agents-md)<a href="https://agentmods.dev/instructions/hanzhi0807/document-buddy/agents-md"><img src="https://agentmods.dev/badge/instructions/hanzhi0807/document-buddy/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 | $0.00295 | $0.00295 |
| Opus 5 | $0.00148 | $0.00148 |
| Sonnet 5 | $0.00059 | $0.00059 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
document-buddy 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 3d 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
Agent 接力规则
这个仓库会被多个 agent 轮流继续开发。每个 agent 开始工作前必须先阅读：
README.mddocs/agent-handoff.md- 与当前任务相关的
docs/*.md
每个 agent 完成工作后，必须在最终回复前更新 docs/agent-handoff.md，不需要等待用户再次提醒。
更新交接文档时至少写清楚：
- 本轮做了什么。
- 改了哪些关键文件。
- 跑了哪些验证命令，结果如何。
- 当前还没做什么。
- 下一位 agent 应该从哪里继续。
- 如果相关 commit 已经生成，写上 commit hash；如果当前提交尚未生成，最终回复里必须补充最新 hash。
项目方向提醒：
- 产品名：文档搭子 / Document Buddy。
- 正式目标：把团队可见的 wiki 做到飞书知识库或飞书云文档里。
- 当前形态：无服务端 MCP 工具包，不做 SaaS、不做 webhook、不保存飞书 token、不保存 LLM API key。
- 本地
WORK_MEMORY_DATA_DIR只作为缓存、索引、冲突状态和离线 fallback。 - 回答项目问题前必须调用
query_project_wiki或get_cited_context，没有 citations 就不能编答案。
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.
- 3d ago First seen · 26 lines · 295 tokens per session scan A a596ad2421f5
document-buddy AGENTS.md is an instructions file published in the GitHub repository Hanzhi0807/document-buddy (1 stars, last pushed 2mo ago), licensed MIT. It adds 295 tokens to every session, about $0.0015 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
pdf-reader-mcp AGENTS.md
AGENTS.md instructions for SylphxAI/pdf-reader-mcp, covering pdf-reader-mcp — local agent notes only, boundary hazards, local commands, validation notes and backend false-authority fence.
lastsearch CLAUDE.md
Claude Code instructions for LastSearch-HQ/lastsearch, covering claude.md — lastsearch, what this project is, monorepo structure, two-repo architecture and key commands.
cite-citadel copilot-instructions.md
Instructions for MarkusNeusinger/cite-citadel, covering github copilot instructions — cite-citadel, what this is, commands, test corpora and self-verification (feedback loops).
lark-cli CLAUDE.md
Instructions for yjwong/lark-cli, covering claude code instructions for lark, project structure, build & test, code conventions and commands.
cite-citadel CLAUDE.md
Instructions for MarkusNeusinger/cite-citadel, covering claude.md, what this is, commands, test corpora and self-verification (feedback loops).
trackly-cli CLAUDE.md
Claude Code instructions for trackly-app/trackly-cli, covering trackly-cli, tech stack, backend production source of truth, directory structure and key commands.