What is frostyard-acmm-conformance?

A repository-maintenance guide for meeting Hive ACMM checks, which verify that required files and directories exist at fixed paths.

Use it to review ACMM issues, map each requirement to an existing canonical file, add relative symlinks or directory trees where needed, and record the mapping in an architecture decision record.

It helps satisfy those checks without creating duplicate copies of existing content.

How frostyard/snosi configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to frostyard/snosi. 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/frostyard/snosi/main/.agents/skills/frostyard-acmm-conformance/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/frostyard/snosi

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/frostyard/snosi/frostyard-acmm-conformance/github.svg)](https://agentmods.dev/skills/frostyard/snosi/frostyard-acmm-conformance)

Your own site

<a href="https://agentmods.dev/skills/frostyard/snosi/frostyard-acmm-conformance"><img src="https://agentmods.dev/badge/skills/frostyard/snosi/frostyard-acmm-conformance/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/frostyard/snosi/frostyard-acmm-conformance"><img src="https://agentmods.dev/badge/skills/frostyard/snosi/frostyard-acmm-conformance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,146 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original 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	$0.00126	$0.02146
Opus 5.5	$0.00050	$0.00858
Sonnet 5.5	$0.00025	$0.00429
Haiku 4.5	$0.00013	$0.00215

Measured 2mo ago against content hash f4c3453fd3c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

frostyard-acmm-conformance 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/frostyard-acmm-conformance/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

frostyard-acmm-conformance — satisfy ACMM criteria without duplicating content

The Hive ACMM evaluation grades repositories by checking that fixed paths exist. Each generated issue lists acceptable paths and states "the content can follow your project's conventions" — satisfying any one listed path satisfies the criterion, and only existence is checked. The frostyard answer (core ADR-0029) is: never create a second copy of anything. Done looks like: every acmm issue closable by one PR, scripts/check-docs.mjs green, zero duplicated content, and the alias table registered in a repo-local ADR.

Precedents to imitate: core's own conformance (core ADR-0029, core#22–#40) and repogen's (repogen ADR-0012, repogen#37–#55).

Steps

Inventory the issues. gh issue list --repo frostyard/<repo> --label acmm --state open --json number,title,body. Build a table: issue → criterion ID (acmm:*) → accepted paths. Set aside anything in the range that is not a file-existence criterion (substantive engineering issues, hold labels, already-merged PRs) — those are separate work items; never close them from the conformance PR.
Classify each criterion with three questions, in order:
- Does canonical content already exist? → relative symlink to it.
- Is the accepted path a directory? → real git tree (an evaluator reading the tree API sees a symlink as a blob, not a tree; put a README.md inside so the tree exists, and symlink any payload inside it if the payload lives elsewhere).
- Nothing canonical? → new artifact that does real work — never a content-free stub.
Unify the instruction surface first (usually criteria agents-md, contrib-guide, cursor-rules, simple-skills). Merge every existing instruction file (CLAUDE.md, .github/copilot-instructions.md, …) into one canonical AGENTS.md — keep all content, deduplicate overlap, keep it tool-agnostic — then replace the old files with symlinks: CLAUDE.md, GEMINI.md, CONTRIBUTING.md, .cursorrules → AGENTS.md; .github/copilot-instructions.md → ../AGENTS.md; .claude/skills → ../.agents/skills. Targets are always relative, computed from the alias's own directory. AGENTS.md opens with a header naming its alias set, and gains the rule "conformance alias symlinks are listed in ADR-NNNN — edit their canonical targets, never the aliases."

Read the full file on GitHub · 121 lines

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.

.synced-from-core 157 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 · 121 lines · 126 tokens per session scan A f4c3453fd3c7

Subscribe to this mod's changes

frostyard-acmm-conformance is a skill published in the GitHub repository frostyard/snosi (32 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 2,146 once invoked, about $0.0005 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.

Git and workflow

frostyard-acmm-conformance next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
frostyard-acmm-conformancefrostyard/snosi	Skill	32	today	MIT	A	126	Claude Code, Codex
merge-batchdiegosouzapw/OmniRoute	Skill	83k	5d ago	MIT	A	46	Claude Code
prowler-commitprowler-cloud/prowler	Skill	15k	yesterday	Apache-2.0	A	44	Claude Code, Codex
gh-auth-isolationgithub/gh-aw	Skill	5.6k	yesterday	MIT	A	20	Claude Code, Codex
github-skillzeenie-ai/OpenCompany	Skill	1.1k	yesterday	MIT	A	51	Claude Code
comet-githubrpamis/comet	Skill	3.3k	yesterday	MIT	A	72	Claude Code, Codex
release-helperSahir619/fable-method	Skill	2.3k	1mo ago	MIT	A	43	Claude Code

snosi: Skill for Claude Code