Borrowing it
Nothing to install: this file belongs to illodev/workfile. 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/illodev/workfile/main/CLAUDE.mdgit clone --depth 1 https://github.com/illodev/workfileWrote 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/illodev/workfile/claude-md)<a href="https://agentmods.dev/instructions/illodev/workfile/claude-md"><img src="https://agentmods.dev/badge/instructions/illodev/workfile/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/illodev/workfile/claude-md"><img src="https://agentmods.dev/badge/instructions/illodev/workfile/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 | $0.00277 | $0.00277 |
| Opus 5.5 | $0.00111 | $0.00111 |
| Sonnet 5.5 | $0.00055 | $0.00055 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
workfile 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.
This is a copy
86% identical to workfile AGENTS.md — 4 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.
What it actually says
Workfile for Claude Code
Before substantial changes, read .project/agents/protocol.md and the relevant workflow under .project/agents/workflows.
Critical rules:
- Search context with
pnpm workfile searchorpnpm workfile agents context. - Claim cards before modifying their scope.
- Use CLI/MCP for protocol mutations.
- Two exits, and say which:
reviewonly when every criterion is met and just runtime evidence is missing; otherwisenext/blockedwith the reason in a note.reviewis not "my turn ended". donerequires evidence from where the change actually runs.- Acceptance criteria live under
## Acceptance criteria; checkboxes are only for criteria; a criterion with a false premise is rewritten with the measurement, not left unmarked. - Finish discovered work rather than carding it when it is the same file and the same run; card what you cannot do, and record durable knowledge.
- Run
pnpm workfile doctorbefore finishing.
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 e1ded6198db6
- 1mo ago Changed c0f90919aaa5
- 2mo ago Changed 86747247c01c
- 2mo ago Changed · +2 lines · +96 tokens per session 56cdae5a3758
- 2mo ago First seen · 15 lines · 181 tokens per session scan A 2c2c8864e0ac
workfile CLAUDE.md is an instructions file published in the GitHub repository illodev/workfile (3 stars, last pushed 5d ago), licensed MIT. It adds 277 tokens to every session, about $0.0011 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to workfile AGENTS.md, differing in 4 lines, and is treated as a copy.
workfile CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| workfile CLAUDE.mdillodev/workfile | Instructions file | 3 | 5d ago | MIT | A | 277 | 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 |