Borrowing it
Nothing to install: this file belongs to acaprino/daodan. 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/acaprino/daodan/master/CLAUDE.mdgit clone --depth 1 https://github.com/acaprino/daodanWrote 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/acaprino/daodan/claude-md)<a href="https://agentmods.dev/instructions/acaprino/daodan/claude-md"><img src="https://agentmods.dev/badge/instructions/acaprino/daodan/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/acaprino/daodan/claude-md"><img src="https://agentmods.dev/badge/instructions/acaprino/daodan/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 | $0.16917 | $0.16917 |
| Opus 5.5 | $0.06767 | $0.06767 |
| Sonnet 5.5 | $0.03383 | $0.03383 |
| Haiku 4.5 | $0.01692 | $0.01692 |
Grade A, and why
daodan 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 4d 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.
This is a copy
94% identical to daodan AGENTS.md — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 691 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daodan
The Daodan is the symbiote that augments its host. This repository is the Daodan of coding agents: a development harness, built on the static Meta-Code map of codebase-map, that coordinates project intent, code, meaningful tests, durable knowledge and experimental artifacts, alongside core language and stack specialists, Office methods, domain verticals and web research. The 24 domain, office, research and framework plugins extracted to acaprino/shinatama in marketplace 36.0.0 returned to this single marketplace, with text-humanizer back as a local dependency and /daodan:humanize-text restored to the daodan entry plugin while domain verticals keep their own workflow namespaces. skill-catalog discovers every plugin's knowledge sidecars and selects them per run. It ships to five hosts from one source. Remote: acaprino/daodan on GitHub.
Development harness
codebase-map is the core of the harness. Its static analysis records a project as Meta-Code: file and symbol inventory, body, interface and effects digests, interconnections and persistent semantic cards with surgical freshness. senior-review, abstraction-architect, project-knowledge, project-delivery and project-lifecycle require it and build their understanding on its evidence rather than rediscovering the project. The map supplies evidence and leads, never verdicts: correctness, documentation, tests and cleanup stay with their owners, who confirm a lead by reading source. Leaf and specialist plugins such as work-controller, skill-catalog, repo-hygiene, testing, clean-code and the language plugins do not depend on it.
Every core harness command lives in one entry plugin, daodan, since marketplace 38.0.0 (the command set design of
2026-10-19, a record retired with docs/superpowers/ on 2026-11-01): one command per
intention, no parameters, the only argument free text. Authorizations are asked
when a step needs them, once, and recorded in the run. Each command is a thin
entry into its owner's method; every core specialist plugin keeps skills, roles and
contracts and has no command. A specialist method a command used to carry lives
in its owner's skill, where the entry loads it by name. Independent domain verticals (research, digital-marketing, trading-broker-integration, pwa-expert, browser-extensions, grabber-development, libgdx-development, marketplace-ops, opentelemetry, rag-development, stripe, system-utils, xterm, ai-tooling, frontend-review, learning) keep their own workflow namespaces.
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.
- 4d ago Changed · -74 tokens per session e669db76abf7
- 5d ago Changed · +6 lines · +226 tokens per session d7715b62b3f0
- 8d ago Changed · +8 lines · +122 tokens per session 4d10247b23bb
- 9d ago Changed · +37 lines · +630 tokens per session e379d236582f
- 10d ago Changed · +20 lines · +611 tokens per session 27c7a5fc70ef
- 11d ago Changed · +42 lines · +682 tokens per session f68b0b2eaedb
- 12d ago Changed · +13 lines · +220 tokens per session 878a44c0c76d
- 13d ago Changed · +25 lines · +356 tokens per session 76a75d78bee9
- 14d ago Changed · +5 lines · +91 tokens per session 448171eea8dc
- 18d ago First seen · 535 lines · 14,053 tokens per session scan A 98bf625e6a46
daodan CLAUDE.md is an instructions file published in the GitHub repository acaprino/daodan (9 stars, last pushed 4d ago), licensed MIT. It adds 16,917 tokens to every session, about $0.0677 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to daodan AGENTS.md, differing in 10 lines, and is treated as a copy.
daodan CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| daodan CLAUDE.mdacaprino/daodan | Instructions file | 9 | 4d ago | MIT | A | 16,917 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |