argentum-engine: Skill for Claude Code

.agents/skills/assay-loop/SKILL.md

assay-loop is a skill for Claude Code from wingedsheep/argentum-engine. It costs 115 tokens per session (3,524 once invoked), scanned B, original, no licence file.

An agent loop that expands Argentum Assay's grammar one reviewed pull request at a time. A pull request is a proposed code change for review; the loop reads Oracle text that the existing engine and SDK already support.

In plain words
What is it for?
Use it to drive reviewed pull requests that extend the Assay grammar under its existing vocabulary and labelling rules.
Why use it?
It provides a continuing process for adding supported grammar without duplicating cards that were written manually or introducing new SDK terms.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is wingedsheep/argentum-engine's own configuration. It tells Claude Code how to work on argentum-engine 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 argentum-engine configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wingedsheep/argentum-engine. 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/wingedsheep/argentum-engine/main/.agents/skills/assay-loop/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/wingedsheep/argentum-engine

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.

agentmods badge for assay-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/wingedsheep/argentum-engine/assay-loop/github.svg)](https://agentmods.dev/skills/wingedsheep/argentum-engine/assay-loop)
Your own site
<a href="https://agentmods.dev/skills/wingedsheep/argentum-engine/assay-loop"><img src="https://agentmods.dev/badge/skills/wingedsheep/argentum-engine/assay-loop/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 assay-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/wingedsheep/argentum-engine/assay-loop"><img src="https://agentmods.dev/badge/skills/wingedsheep/argentum-engine/assay-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,524 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00115 $0.03524
Opus 5.5 $0.00046 $0.01410
Sonnet 5.5 $0.00023 $0.00705
Haiku 4.5 $0.00012 $0.00352

Measured 29d ago against content hash e1fdfc679d2f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

assay-loop 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 29d 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.

a. PICK — one subagent: "In <worktree>, run `just assay-report --implemented --rank tail --top 40`. Read `.claude/loop-runs/assay-grammar.md` and skip every family already marked there (any status). If `backlog/assay-eng
.agents/skills/assay-loop/SKILL.md · 116 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.

  1. 29d ago First seen · 116 lines · 115 tokens per session scan B e1fdfc679d2f

Subscribe to this mod's changes

assay-loop is a skill published in the GitHub repository wingedsheep/argentum-engine (81 stars, last pushed today), with no licence file. It adds 115 tokens to every session and 3,524 once invoked, about $0.0005 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 2026-10-01.

Related

Other skills, from other repositories