agentmods.dev

hipfire: Skill for Claude Code

.agents/skills/hipfire-autoheal/SKILL.md

hipfire-autoheal is a skill for Claude Code, Codex from warpfront/hipfire. It costs 79 tokens per session (1,492 once invoked), scanned A, original, no licence file.

A troubleshooting guide for hipfire, including its background service, GPU code, installation, and runtime environment. It covers hangs, port conflicts, missing compiled code, memory exhaustion, and related failures.

In plain words
What is it for?
Use it after diagnostics find a runtime problem, or when hipfire is broken because of stale process files, ROCm paths, missing kernels, out-of-memory errors, compilation failures, or conversation-memory regressions.
Why use it?
It helps connect common failure symptoms to likely causes and repair steps.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing. Also seen: installed under .agents/ (shared by several agents).

This is warpfront/hipfire's own configuration. It tells Claude Code and Codex how to work on hipfire itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hipfire configures →

not rated 797repo +18 changed 9d ago A scan 79 tokens custom licence
View source ↗ warpfront/hipfire
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/.agents/skills/hipfire-autoheal/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/warpfront/hipfire

Made for: Claude Code, Codex.

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 hipfire-autoheal

README.md
[![agentmods](https://agentmods.dev/badge/skills/warpfront/hipfire/hipfire-autoheal/github.svg)](https://agentmods.dev/skills/warpfront/hipfire/hipfire-autoheal)
Your own site
<a href="https://agentmods.dev/skills/warpfront/hipfire/hipfire-autoheal"><img src="https://agentmods.dev/badge/skills/warpfront/hipfire/hipfire-autoheal/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.

agentmods 80×15 button for hipfire-autoheal

Your own site · 80×15
<a href="https://agentmods.dev/skills/warpfront/hipfire/hipfire-autoheal"><img src="https://agentmods.dev/badge/skills/warpfront/hipfire/hipfire-autoheal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,492 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.01492
Opus 5.5 $0.00032 $0.00597
Sonnet 5.5 $0.00016 $0.00298
Haiku 4.5 $0.00008 $0.00149

Measured 9d ago against content hash c9fc59f24b19, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hipfire-autoheal 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (triage.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| **Safe automatic** | Read-only triage/diag; `hipfire ps`; `curl` `/health`; one-shot env on a **confirmed local** daemon path (`HIPFIRE_LOCAL=1` / no resident serve — see bisection); `HIPFIRE_HIPCC_EXTRA_FLAGS`; `tail`
.agents/skills/hipfire-autoheal/SKILL.md · 98 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

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago Changed c9fc59f24b19
  2. 1mo ago Changed fb1c38214b6e
  3. 2mo ago First seen · 98 lines · 79 tokens per session scan A 9244f68f1b92

Subscribe to this mod's changes

hipfire-autoheal is a skill published in the GitHub repository warpfront/hipfire (797 stars, last pushed yesterday), with no licence file. It adds 79 tokens to every session and 1,492 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

DebuggingDevOps and cloudQuantizationamd-gpugpu-computinghipllm-inferencemachine-learning
Related

hipfire-autoheal compared with skills from other repositories

hipfire-autoheal next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
hipfire-autohealwarpfront/hipfireSkill797yesterdaynoneA79Claude Code, Codex
developing-with-streamlitstreamlit/streamlitSkill46kyesterdayApache-2.0A146Claude Code
rocketride-debugging-pipelinesrocketride-org/rocketride-serverSkill20kyesterdayMITA67Claude Code, Codex
trulens-instrumentationtruera/trulensSkill3.6kyesterdayMITA25Claude Code, Codex
trulens-diagnosistruera/trulensSkill3.6kyesterdayMITA17Claude Code, Codex
neuron-monitoringneuron-core/neuron-aiSkill2.2kyesterdayMITA80Claude Code, Codex
plano-observability-debuggingkatanemo/planoSkill7.1k13d agoApache-2.0A32Claude Code, Codex