What is hipfire CLAUDE.md?

Project-specific instructions for Claude Code when working on hipfire, a Rust inference engine for AMD RDNA graphics processors. They cover the project’s purpose, architecture, firmware status, building, testing, and required checks.

Developing, building, testing, or reviewing changes in the warpfront/hipfire repository.

They give an AI coding assistant the context and working rules needed to change this particular project correctly. Without them, the assistant may miss project-specific build or test requirements.

How warpfront/hipfire configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to warpfront/hipfire. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/warpfront/hipfire/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/warpfront/hipfire

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/warpfront/hipfire/claude-md/github.svg)](https://agentmods.dev/instructions/warpfront/hipfire/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/warpfront/hipfire/claude-md"><img src="https://agentmods.dev/badge/instructions/warpfront/hipfire/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/warpfront/hipfire/claude-md"><img src="https://agentmods.dev/badge/instructions/warpfront/hipfire/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 7,204 This file is loaded in full into every session.

When invoked 7,204 The same file — it is already loaded in full.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin unknown 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.

Model	Per session	Once invoked
Fable 5.1	$0.07204	$0.07204
Opus 5.5	$0.02882	$0.02882
Sonnet 5.5	$0.01441	$0.01441
Haiku 4.5	$0.00720	$0.00720

Measured 9d ago against content hash a6100eb6dab9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

hipfire CLAUDE.md scanned grade B with 1 finding 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Opt in per-machine by adding to `~/.claude/settings.json`:

CLAUDE.md · 493 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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.

9d ago Changed · +1 lines · +12 tokens per session a6100eb6dab9
13d ago Changed · +7 lines · +155 tokens per session 20d70898d612
23d ago Changed · +15 lines · +275 tokens per session 7131cf5f0938
1mo ago Changed · +8 lines · +128 tokens per session 3475dfdbe549
2mo ago Changed · +2 lines · +32 tokens per session 6aef5bf87f9f
2mo ago First seen · 460 lines · 6,602 tokens per session scan B bb070ba9ae6c

Subscribe to this mod's changes

hipfire CLAUDE.md is an instructions file published in the GitHub repository warpfront/hipfire (797 stars, last pushed yesterday), with no licence file. It adds 7,204 tokens to every session, about $0.0288 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Quantization amd-gpu gpu-computing hip llm-inference machine-learning

hipfire CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hipfire CLAUDE.mdwarpfront/hipfire	Instructions file	797	yesterday	none	B	7,204	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	today	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

hipfire: Instructions file for Claude Code