What is nyann CLAUDE.md?

Repository instructions for Claude Code, an AI coding assistant, covering project structure, coding rules, testing, releases, and documentation. They are tailored to the nyann plugin.

Use them when changing nyann, especially for architecture, skills, tests, releases, CI, documentation, or project health checks.

They give the coding assistant consistent project context and rules, reducing mistakes caused by guessing how the repository works.

nyann CLAUDE.md — Instructions file for coding agents by thettwe: Repository instructions for Claude Code, an AI coding assistant…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/thettwe/nyann/claude-md

Clone the repo

git clone --depth 1 https://github.com/thettwe/nyann

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/instructions/thettwe/nyann/claude-md.svg)](https://agentmods.dev/instructions/thettwe/nyann/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/thettwe/nyann/claude-md"><img src="https://agentmods.dev/badge/instructions/thettwe/nyann/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 559 This file is loaded in full into every session.

When invoked 559 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00559	$0.00559
Opus 5	$0.00280	$0.00280
Sonnet 5	$0.00112	$0.00112
Haiku 4.5	$0.00056	$0.00056

Measured 5d ago against content hash 731aac4960eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

nyann CLAUDE.md 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 5d 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.

CLAUDE.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

nyann is a Claude Code plugin that sets up and maintains project governance: git workflow, hooks, branching, commits, releases, CI, docs routing, and health monitoring. See CHANGELOG.md for release history.

Build / lint / test commands:

bats tests/bats/ unit + integration suite
./tests/lint.sh shellcheck + SKILL.md length enforcement (also available as shellcheck bin/*.sh)
claude plugin validate . manifest validation
evals/run.sh skill-level trigger + output-quality evals (run locally; not a PR gate)

Architecture & conventions

Detailed docs (Project Memory):

Topic	Where
Layer model + JSON schema contracts + MCP boundary	`docs/architecture.md`
Non-negotiable conventions (preview-before-mutate, idempotency, router-mode, profiles-as-data, no internal refs)	`docs/principles/conventions.md`
Documentation principles + Project Memory model	`docs/principles/documentation.md`
Release procedure	`docs/RELEASING.md`

Read these before making changes that cross layers, touch generated files, or alter the doc structure.

Skill authoring rules (apply to every `SKILL.md`)

Body ≤ 500 lines. Longer detail → split into skills/<skill>/references/<topic>.md.
Frontmatter description must be pushy: enumerate trigger phrases and scenarios aggressively. Vague descriptions under-trigger.
Imperative + explain-why. Every step says what and because, so Claude can adapt when the step doesn't fit.
Progressive disclosure via references/ (loaded on demand, e.g. per-stack notes).
Bundled scripts/ for repeated work.
Never duplicate content between SKILL.md and references, or between skills.

Scope reminders

Git only. No Mercurial/SVN/Fossil.
GitHub only for remote integration. GitLab/Bitbucket deferred.
No application scaffolding. Not a create-next-app replacement.
No dependency management beyond what hooks require.
No history rewrites. Non-compliant past commits are flagged, not fixed.
Unix-first. Windows (.ps1 variants) deferred.

Read the full file on GitHub · 45 lines

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.

5d ago First seen · 45 lines · 559 tokens per session scan A 731aac4960eb

Subscribe to this mod's changes

nyann CLAUDE.md is an instructions file published in the GitHub repository thettwe/nyann (6 stars, last pushed 6d ago), licensed MIT. It adds 559 tokens to every session, about $0.0028 per session on Opus 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 2026-08-31.

claude-code claude-code-plugin claude-skills github governance scaffolding

recursive-decomposition-skill AGENTS.md

Instructions for massimodeluisa/recursive-decomposition-skill, covering agents: recursive-decomposition skill, read these first (mandatory), language policy, non-negotiables and commands.

massimodeluisa/recursive-decomposition-skill · 321 tokens

curie CLAUDE.md

Claude Code instructions for curie-eng/curie, covering one entry point: curie, release train selection and architecture decision records (adrs).

curie-eng/curie · 1,106 tokens

embedded-systems-architect AGENTS.md

Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.

Zachariah9420/embedded-systems-architect · 177 tokens

octowiz CLAUDE.md

Instructions for raelli/octowiz, covering octowiz, releasing & deploying, commands, agent skills and issue tracker.

raelli/octowiz · 205 tokens

ship-it open-pr.instructions.md

Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…

khrichtchatyi/ship-it · 84 tokens

beacon AGENTS.md

AGENTS.md instructions for chris-peterson/beacon, covering beacon, what beacon is, three deliverables, hard boundaries, hot paths — keep fast and surfaces beacon paints.

chris-peterson/beacon · 7,971 tokens