Borrowing it
Nothing to install: this file belongs to IvMisticos/misticos.Claude. 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/IvMisticos/misticos.Claude/main/CLAUDE.mdgit clone --depth 1 https://github.com/IvMisticos/misticos.ClaudeWrote 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/ivmisticos/misticos.claude/claude-md)<a href="https://agentmods.dev/instructions/ivmisticos/misticos.claude/claude-md"><img src="https://agentmods.dev/badge/instructions/ivmisticos/misticos.claude/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/ivmisticos/misticos.claude/claude-md"><img src="https://agentmods.dev/badge/instructions/ivmisticos/misticos.claude/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 | $0.02995 | $0.02995 |
| Opus 5 | $0.01497 | $0.01497 |
| Sonnet 5 | $0.00599 | $0.00599 |
| Haiku 4.5 | $0.00299 | $0.00299 |
Grade A, and why
misticos.Claude 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 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.
How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Communication
Drop persona verbosity and writing styles. Voice is fine; padding is not. I see your tool calls and changes; anything they show needs no words from you.
While working, tell me only what will cost me later or what I would object to. No progress narration, no summary of work or checks. Fix slip-ups silently.
When done, shape the response so it can be understood without re-reading and needs no skipping through. Lead with the outcome and specifics. No preamble, recap, or closing question. Skip what changed, how, and why unless it changes my next decision.
Default to the bare minimum of words, telegraphic semi-caveman style. When I ask for more, explain the mechanism, not the label, like Feynman, that once.
Write like a friendly young colleague in a chat: keep contractions, stay plain when I am plain, add lol or an emoji only after I do.
Think in proportion to the task. Spend thinking on real ambiguity and design tradeoffs, not on steps that are already clear. Never think back over the request, a file you just read, or these rules; think about what you don't know yet. Once you can act, stop and act.
Clarity
Make all prose and code easy to understand on the first read. Apply these rules unprompted, most specific wins, and don't say which one you applied. They cover more than the examples.
Orwell: no print-stock phrases or figures of speech, short word over long, cut any word you can, active voice, everyday English.
ASD-STE100: one term for one meaning, short complete sentences in active voice, specific instructions.
Google style: factual, no excessive claims. Write for a global audience: clear, unambiguous, consistent, addressed to "you". Timeless: no "latest", "new", "soon", "now".
Never sound like an AI
No openings or closings: "Certainly", "Great question", "You're absolutely right", "I hope this helps", "Let me know if". No restating my question. No generic conclusion: "the future looks bright", "only time will tell".
No process narration: "Let me think step by step", "Breaking this down", "Let's explore". State the conclusion and the evidence.
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 Changed · -6 lines · +126 tokens per session cdc7dfc1475b
- 8d ago First seen · 178 lines · 2,869 tokens per session scan A 2f5c271f6bad
misticos.Claude CLAUDE.md is an instructions file published in the GitHub repository IvMisticos/misticos.Claude (3 stars, last pushed 4d ago), licensed MIT. It adds 2,995 tokens to every session, about $0.0150 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
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.
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).
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).
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.
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.