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.
npx agentmods add instructions/chappygo-os/atomic-spec/claude-mdgit clone --depth 1 https://github.com/Chappygo-OS/Atomic-SpecWrote 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.
[](https://agentmods.dev/instructions/chappygo-os/atomic-spec/claude-md)<a href="https://agentmods.dev/instructions/chappygo-os/atomic-spec/claude-md"><img src="https://agentmods.dev/badge/instructions/chappygo-os/atomic-spec/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.03322 | $0.03322 |
| Opus 5 | $0.01661 | $0.01661 |
| Sonnet 5 | $0.00664 | $0.00664 |
| Haiku 4.5 | $0.00332 | $0.00332 |
Grade A, and why
Atomic-Spec 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 200 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.
What This Repository Is
This is not a runtime application. It is a governance framework for AI-driven development — a customized fork of GitHub's Spec Kit that implements the Atomic Traceability Model. The deliverables are templates, prompts, knowledge stations, and a thin Python CLI. Consumers install this framework into their own projects to constrain how AI coding agents (Claude Code, Gemini, Copilot, Cursor, Windsurf, and ~13 others) generate code.
Inspired by Leapable's "Stop Vibe Coding (Until You Do This)" video. The core premise: AI agents produce drift unless forced through gated, atomic, context-pinned phases.
The Nine Prime Directives (memory/constitution.md, Article IX)
These are the non-negotiable rules that every command in this framework enforces. When working in this repo, never weaken or bypass them — they are the entire value proposition:
- Directory Supremacy — every feature gets
index.md+traceability.md - Atomic Injunction —
/atomicspec.tasksis FORBIDDEN from creating a singletasks.md. It must create atasks/directory with individualT-XXX-[name].mdfiles - Context Pinning — during
/atomicspec.implement, the AI may ONLY readindex.md, the current task file, andtraceability.md. Readingplan.mdorspec.mdduring implementation is forbidden - Gate Compliance — Knowledge Station gate criteria must pass before phase transitions
- Knowledge Routing — unknown decisions consult the Station Map first, then the specific station
- Human-In-The-Loop —
/atomicspec.planpauses at 4 mandatory checkpoints (tech stack, validation, UI, registry sync) - Project Defaults Registry — all commands read
specs/_defaults/registry.yamland enforce project-wide standards - Self-Contained Tasks — task files embed all context (registry values, domain rules, gate criteria) needed for execution under Context Pinning
- Orientation Read Surface (v0.3+) —
/atomicspec.implementPhase 0 detects cross-provider handoff state viastamp-lifecycle statuson artifact Lifecycle Markers; direct body reads ofplan.md/spec.md/clarify-log.mdremain forbidden, even during orientation. Sibling control to Directive 3; does NOT widen it.
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.
- 4d ago First seen · 200 lines · 3,322 tokens per session scan A 61484038ee2d
Atomic-Spec CLAUDE.md is an instructions file published in the GitHub repository Chappygo-OS/Atomic-Spec (10 stars, last pushed 11d ago), licensed MIT. It adds 3,322 tokens to every session, about $0.0166 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.
Other instructions, from other repositories
prp-manager CLAUDE.md
Instructions for willywg/prp-manager, covering claude.md, project overview, repository structure, key concepts and three workflows.
superpowers-zh CLAUDE.md
Claude Code instructions for jnMetaCode/superpowers-zh, covering superpowers — 贡献者指南, 如果你是 ai agent, pull request 要求, 我们不会接受的内容 and 第三方依赖.
spec-kit-zh AGENTS.md
AGENTS.md instructions for loulanyue/spec-kit-zh, covering agents.md, about spec kit and specify, general practices, adding new agent support and current supported agents.
Meta_Kim CLAUDE.md
Claude Code instructions for KimYx0207/Meta_Kim, covering metakim for claude code, fast read, what this repository is, claude code's role and canonical vs runtime files.
nopua AGENTS.md
Instructions for wuji-labs/nopua, covering nopua · codex 入仓规则, 一 · 项目定位, 二 · 起手必读, 三 · 工程与研究纪律 and 四 · 对外署名.
decantr CLAUDE.md
Instructions for decantr-ai/decantr, covering claude.md -- decantr, project, packages, apps and terminology.