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/xhulz/raze/claude-mdgit clone --depth 1 https://github.com/xhulz/razeWrote 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/xhulz/raze/claude-md)<a href="https://agentmods.dev/instructions/xhulz/raze/claude-md"><img src="https://agentmods.dev/badge/instructions/xhulz/raze/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 | $0.00278 | $0.00278 |
| Opus 5 | $0.00139 | $0.00139 |
| Sonnet 5 | $0.00056 | $0.00056 |
| Haiku 4.5 | $0.00028 | $0.00028 |
Grade A, and why
raze 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.
What it actually says
CLAUDE.md
The .ia/ directory is the source of truth for all development work in this repository.
Before acting on any task
- Read
.ia/rules.md— hard constraints and anti-hallucination rules. Follow them without exception. - Read
.ia/routing.md— classify the task and determine the agent sequence. - Follow
.ia/retrieval/playbook.mdto select which context files to read before touching code.
Memory
.ia/memory/invariants.mdmust be read before any non-trivial code change..ia/memory/decisions.mdmust be read before any refactor or architecture work..ia/memory/open-questions.mdsignals unstable areas — treat them as uncertain until resolved.- Write to memory only when a decision, constraint, or open question is durable and affects future behavior.
Navigation
.ia/index.mdmaps task types and target areas to the right files..ia/retrieval/file-map.mdmaps areas to source paths..ia/context/holds architecture, module, convention, and domain context.
Do not
- Act on assumptions when the source file can be read directly.
- Propose changes across multiple modules without planning first.
- Write to memory for transient observations or in-progress state.
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 First seen · 29 lines · 278 tokens per session scan A 3ccece9437cc
raze CLAUDE.md is an instructions file published in the GitHub repository xhulz/raze (5 stars, last pushed 5mo ago), licensed MIT. It adds 278 tokens to every session, about $0.0014 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
foundry-template AGENTS.md
Instructions for PaulRBerg/foundry-template, covering agents.md, stack, commands, forge and bun scripts (package.json).
PROGRAMMABLE AGENTS.md
AGENTS.md instructions for programmablehq/PROGRAMMABLE, covering programmable workspace rules, canonical repository, parallel work, path ownership and release discipline.
foundry-template CLAUDE.md
Instructions for PaulRBerg/foundry-template, a project described as: Foundry-based template for developing Solidity smart contracts.
prb-math AGENTS.md
Instructions for PaulRBerg/prb-math, covering prbmath, stack, structure, commands and development.
evmole AGENTS.md
Instructions for cdump/evmole: EVMole extracts structured facts from deployed EVM runtime bytecode.
solidity-language-server AGENTS.md
Instructions for asyncswap/solidity-language-server, covering agents, prerequisites: ast identity model, the two id types, the src string format and why file ids are unstable from solc.