A guide for testing and comparing ways to shrink and run AI models. It covers calibration experiments, quality checks, file-format choices, weight transformations, and memory use during model operation.

Use it when comparing compressed model formats, measuring response quality or perplexity, planning weight changes, or deciding how the model should use memory while running.

It helps evaluate whether a model version is suitable to keep, package, reject, or send onward, based on quality and hardware fit.

How warpfront/hipfire configures Codex

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/astrea/SKILL.md

Clone the repo

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

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/warpfront/hipfire/astrea/github.svg)](https://agentmods.dev/skills/warpfront/hipfire/astrea)

Your own site

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

Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,653 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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	$0.00080	$0.02653
Opus 5.5	$0.00032	$0.01061
Sonnet 5.5	$0.00016	$0.00531
Haiku 4.5	$0.00008	$0.00265

Measured 2mo ago against content hash edcb997331a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

astrea 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 2mo 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.

.agents/skills/astrea/SKILL.md · 178 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

1 file 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.

agents/openai.yaml 395 B

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.

2mo ago First seen · 178 lines · 80 tokens per session scan A edcb997331a5

Subscribe to this mod's changes

astrea is a skill published in the GitHub repository warpfront/hipfire (797 stars, last pushed yesterday), with no licence file. It adds 80 tokens to every session and 2,653 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.

Data and AI Quantization amd-gpu gpu-computing hip llm-inference machine-learning

astrea next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
astreawarpfront/hipfire	Skill	797	yesterday	none	A	80	Codex
hugging-face-model-trainerpatchy631/ai-engineering-hub	Skill	41k	5d ago	MIT	A	131	Claude Code
hugging-face-datasetspatchy631/ai-engineering-hub	Skill	41k	5d ago	MIT	A	49	Claude Code
rocketride-building-pipelinesrocketride-org/rocketride-server	Skill	20k	yesterday	MIT	A	66	Claude Code, Codex
rocketride-running-pipelinesrocketride-org/rocketride-server	Skill	20k	yesterday	MIT	A	48	Claude Code, Codex
pysrastroautomata/PySR	Skill	4.2k	4d ago	Apache-2.0	A	61	Claude Code, Codex
trulens-evaluation-setuptruera/trulens	Skill	3.6k	yesterday	MIT	A	17	Claude Code, Codex

hipfire: Skill for Codex