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/sepahead/crebain/claude-mdgit clone --depth 1 https://github.com/sepahead/crebainWrote 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/sepahead/crebain/claude-md)<a href="https://agentmods.dev/instructions/sepahead/crebain/claude-md"><img src="https://agentmods.dev/badge/instructions/sepahead/crebain/claude-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 | $0.00560 | $0.00560 |
| Opus 5 | $0.00280 | $0.00280 |
| Sonnet 5 | $0.00112 | $0.00112 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
crebain 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 5d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CREBAIN Claude guide
Follow all repository instructions in AGENTS.md. The instructions
in that file are authoritative for commands, code style, architecture, tests,
and documentation consistency.
Documentation style
Use the principles of ASD-STE100 Simplified Technical English, Issue 9 for new or changed technical prose. The official ASD-STE100 site identifies Issue 9, dated January 15, 2025, as the current standard. These rules are the CREBAIN house-style adaptation. Do not claim that a document fully conforms to ASD-STE100 unless a qualified review verifies it.
- Use American English and approved project terminology. Use one technical term for one concept.
- Write short, direct sentences. Use no more than 20 words in a procedural sentence and 25 words in a descriptive sentence when practical.
- Give one instruction in each numbered step. Use the imperative form for instructions.
- Put a condition before the action that depends on it.
- Use active voice. Use passive voice only when the actor is unknown or the actor is less important than the action.
- Give one topic in each sentence. Keep related sentences in one paragraph, and use no more than six sentences in a paragraph when practical.
- Use a vertical list for complex information. Do not use semicolons in prose.
- Define each abbreviation at its first use. Do not change exact identifiers, command names, code, protocol terms, quoted text, or required legal text.
- Use requirement words consistently:
muststates a requirement,must notstates a prohibition,maygives permission, andcanstates capability. Do not replace these words if the replacement changes the contract. - Use
WARNINGfor a risk of injury or death. UseCAUTIONfor a risk of damage. Start the safety instruction with a command or condition, then state the possible result. - Do not use slang, unexplained jargon, Latin abbreviations, or a word-for-word substitution that changes the meaning. Rewrite the sentence when necessary.
- Treat CREBAIN names, source identifiers, API names, and domain-specific vocabulary as technical terms. Keep their spelling consistent.
- Preserve the meaning of historical records, frozen evidence, generated files, vendored documentation, quotations, licenses, and codes of conduct.
- Give each complex SVG diagram concise alt text and an adjacent prose text alternative. Keep each SVG self-contained and accessible.
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.
- 5d ago First seen · 44 lines · 560 tokens per session scan A c775d1238cd7
crebain CLAUDE.md is an instructions file published in the GitHub repository sepahead/crebain (21 stars, last pushed 7d ago), licensed Apache-2.0. It adds 560 tokens to every session, about $0.0028 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 2026-08-30.
Other instructions, from other repositories
ai-engineering-from-scratch AGENTS.md
Instructions for rohitg00/ai-engineering-from-scratch, covering agents.md, philosophy, repo layout, hard rules and dependencies.
FluidAudio copilot-instructions.md
Copilot instructions for FluidInference/FluidAudio, covering fluidaudio - agent development guide, build & test commands, architecture, critical rules and code style (swift-format config).
pixeltable CLAUDE.md
Claude Code instructions for pixeltable/pixeltable, covering claude.md, protected configuration, project overview, repository structure and setup commands.
pixeltable AGENTS.md
AGENTS.md instructions for pixeltable/pixeltable, covering agents.md, protected configuration, project overview, repository structure and setup commands.
speech-swift AGENTS.md
AGENTS.md instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.
watch-skill AGENTS.md
AGENTS.md instructions for oxbshw/watch-skill, covering working on watch skill, what this project is, layout, commands and rules that are not negotiable.