What is frostyard-repo-docs?

A documentation workflow for repositories that keeps architecture decisions, design explanations, exact technical contracts, and implementation plans in separate folders. An ADR is a record of why a major design choice was made.

Use it to create or migrate a repository's docs, maintain architecture and design documents, define interfaces and formats, track phased plans, and keep a searchable documentation index.

It gives developers and coding agents one predictable place to find and maintain project documentation. It also moves older documentation trees into the shared structure and incorporates recorded project learnings.

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-repo-docs/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-repo-docs/github.svg)](https://agentmods.dev/skills/frostyard/snosi/frostyard-repo-docs)

Your own site

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

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,660 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	$0.00119	$0.01660
Opus 5.5	$0.00048	$0.00664
Sonnet 5.5	$0.00024	$0.00332
Haiku 4.5	$0.00012	$0.00166

Measured 2mo ago against content hash 0086f9e1fc27, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

frostyard-repo-docs 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-repo-docs/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

frostyard-repo-docs — core's docs shape, in every repo

Every frostyard repo keeps one documentation tree, docs/, in the same shape as frostyard/core's (core ADR-0025):

Directory	Question	Contents
`docs/adr/`	Why did we choose this?	Repo-local ADRs — immutable once accepted; org-wide decisions go to core instead
`docs/design/`	How does it fit together?	Living architecture docs; `overview.md` is the entry point
`docs/specs/`	What exactly is the contract?	Precise interface/format definitions, changed only alongside code
`docs/plans/`	When/in what order do we build?	Phased plans with "Done when" outcomes

docs/README.md carries this table plus an index of every doc. docs/org-adrs.md lists the core ADRs binding the repo, linked from the index. There is no separate "AI docs" directory — all docs are written to be maximally useful in an agent's context window (style rules below). This skill descends from the retired yeti service's doc-maintainer job (prompt).

Step 0 — Scaffold and migrate (once per repo)

If the repo lacks the shape, or still has a yeti//cairn/ tree:

Create the four category directories and seed each with core's canonical template (do not invent your own): https://raw.githubusercontent.com/frostyard/core/main/docs/<category>/TEMPLATE.md for adr, design, specs, plans.
Create docs/README.md modeled on https://raw.githubusercontent.com/frostyard/core/main/docs/README.md: the category table, an index section per category, and the conventions block (new docs start from the category TEMPLATE; new decision → new ADR with the next number; adding a doc means indexing it). Index every pre-existing docs/*.md file where it stands — do not force-move uncategorized process docs; categorize them opportunistically later.
Migrate the legacy tree with git mv:
- OVERVIEW.md → docs/design/overview.md
- contract/reference docs (APIs, file formats, config references) → docs/specs/<name>.md; other subsystem docs → docs/design/<name>.md
- learnings/* → fold each into the right doc now and delete it; a learning not yet foldable moves to the .memory/ inbox.

Read the full file on GitHub · 110 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 150 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 · 110 lines · 119 tokens per session scan A 0086f9e1fc27

Subscribe to this mod's changes

frostyard-repo-docs is a skill published in the GitHub repository frostyard/snosi (32 stars, last pushed today), licensed MIT. It adds 119 tokens to every session and 1,660 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.

Writing and docs

frostyard-repo-docs next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
frostyard-repo-docsfrostyard/snosi	Skill	32	today	MIT	A	119	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

snosi: Skill for Claude Code