raze CLAUDE.md

raze CLAUDE.md is an instructions file for coding agents from xhulz/raze. It costs 278 tokens per session, scanned A, original, MIT.

Repository instructions for the Raze codebase that tell a coding agent which guidance and project notes to read before changing files.

In plain words
What is it for?
Use them to plan coding tasks, find the right files, follow project constraints, and avoid relying on assumptions.
Why use it?
They reduce guesswork by pointing to the repository’s rules, task routing, architecture notes, and recorded decisions.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/xhulz/raze/claude-md
Clone the repo
git clone --depth 1 https://github.com/xhulz/raze

Wrote 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.

agentmods badge for raze CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/xhulz/raze/claude-md.svg)](https://agentmods.dev/instructions/xhulz/raze/claude-md)
Your own site
<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>
Per session 278 This file is loaded in full into every session.
When invoked 278 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash 3ccece9437cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

CLAUDE.md · 29 lines

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

  1. Read .ia/rules.md — hard constraints and anti-hallucination rules. Follow them without exception.
  2. Read .ia/routing.md — classify the task and determine the agent sequence.
  3. Follow .ia/retrieval/playbook.md to select which context files to read before touching code.

Memory

  • .ia/memory/invariants.md must be read before any non-trivial code change.
  • .ia/memory/decisions.md must be read before any refactor or architecture work.
  • .ia/memory/open-questions.md signals 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.
  • .ia/index.md maps task types and target areas to the right files.
  • .ia/retrieval/file-map.md maps 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.
Changes

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.

  1. 4d ago First seen · 29 lines · 278 tokens per session scan A 3ccece9437cc

Subscribe to this mod's changes

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.