hipfire AGENTS.md

Contributor instructions for hipfire, a Rust inference engine for AMD RDNA graphics processors. They explain the project notice, expectations for AI agents, and the project’s testing procedure.

In plain words
What is it for?
Making or reviewing changes in the warpfront/hipfire repository, especially changes that need project-specific testing.
Why use it?
They help coding agents understand the repository’s rules and verify changes with the expected checks. This avoids treating the project like an ordinary codebase with undocumented requirements.

Instructions file for CodexOpenCode

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/warpfront/hipfire/agents-md
Clone the repo
git clone --depth 1 https://github.com/warpfront/hipfire

Made for: Codex, OpenCode.

Per session 9,666 This file is loaded in full into every session.
When invoked 9,666 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.09666 $0.09666
Opus 5 $0.04833 $0.04833
Sonnet 5 $0.01933 $0.01933
Haiku 4.5 $0.00967 $0.00967

Measured 3d ago against content hash 6de0a8c44224, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hipfire AGENTS.md scanned grade A 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 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

directly, or `exec:nodejs` with `execSync('rg -n PATTERN')`.
AGENTS.md · 699 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

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.

  1. 3d ago First seen · 699 lines · 9,666 tokens per session scan A 6de0a8c44224

Subscribe to this mod's changes

hipfire AGENTS.md is an instructions file published in the GitHub repository warpfront/hipfire (565 stars, last pushed 3d ago), with no licence file. It adds 9,666 tokens to every session, about $0.0483 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.