Atomic-Spec AGENTS.md

Atomic-Spec AGENTS.md is an instructions file for Codex, OpenCode from Chappygo-OS/Atomic-Spec. It costs 5,287 tokens per session, scanned A, original, MIT.

Instructions for adding support for another AI coding agent to Atomic Spec, a framework that guides work through Specify, Plan, Tasks, and Implement phases.

In plain words
What is it for?
Use them when extending Atomic Spec with a new agent, updating its templates, or checking how agent matching and support tiers work.
Why use it?
They explain the framework, its command-line setup tool, supported agents, and the conventions needed for a new integration.

Instructions file for CodexOpenCode

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/chappygo-os/atomic-spec/agents-md
Clone the repo
git clone --depth 1 https://github.com/Chappygo-OS/Atomic-Spec

Made for: Codex, OpenCode.

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 Atomic-Spec AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chappygo-os/atomic-spec/agents-md.svg)](https://agentmods.dev/instructions/chappygo-os/atomic-spec/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/chappygo-os/atomic-spec/agents-md"><img src="https://agentmods.dev/badge/instructions/chappygo-os/atomic-spec/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,287 This file is loaded in full into every session.
When invoked 5,287 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.

ModelPer sessionOnce invoked
Fable 5 $0.05287 $0.05287
Opus 5 $0.02644 $0.02644
Sonnet 5 $0.01057 $0.01057
Haiku 4.5 $0.00529 $0.00529

Measured 3d ago against content hash 026da56c4dd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Atomic-Spec AGENTS.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 3d 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.md · 523 lines

How it starts

The opening of the file, as written. The whole thing — 523 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Adding a New AI Agent to Atomic Spec

About Atomic Spec and the atomicspec CLI

Atomic Spec is a governance framework for AI-driven development — a customized fork of GitHub Spec Kit that enforces the Atomic Traceability Model (gated, atomic, context-pinned phases). See atomic-traceability-model.md for the governance model.

The atomicspec CLI (PyPI package: atomic-spec) bootstraps projects with the framework. It sets up the necessary directory structures, templates, and AI-agent integrations to support the four-phase Specify → Plan → Tasks → Implement workflow.

The framework supports 17+ AI coding assistants across two tiers:

  • Supported tier (wired end-to-end, exercised on every release): claude, gemini, copilot, cursor-agent, windsurf
  • Experimental tier (template-enforced governance, best-effort triage): qwen, opencode, codex, kilocode, auggie, codebuddy, qoder, roo, q, amp, shai, bob

Agent matching for subagents is dynamic: keyword overlap between feature descriptions and YAML frontmatter description fields — no hard-coded agent lists in command templates.

This guide explains how to add a new agent to the supported or experimental tier.


General practices

  • Any changes to src/specify_cli/__init__.py require a version rev in pyproject.toml and an entry in CHANGELOG.md.
  • Agent metadata (AGENT_CONFIG and ATOMIC_SPEC_COMMANDS) lives in src/specify_cli/_config.py — a stdlib-only module that the release workflow imports via importlib.util without installing CLI dependencies.

Adding New Agent Support

This section explains how to add support for new AI agents/assistants to the Specify CLI. Use this guide as a reference when integrating new AI tools into the Spec-Driven Development workflow.

Overview

Specify supports multiple AI agents by generating agent-specific command files and directory structures when initializing projects. Each agent has its own conventions for:

Read the full file on GitHub · 523 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.

  1. 3d ago First seen · 523 lines · 5,287 tokens per session scan A 026da56c4dd1

Subscribe to this mod's changes

Atomic-Spec AGENTS.md is an instructions file published in the GitHub repository Chappygo-OS/Atomic-Spec (10 stars, last pushed 10d ago), licensed MIT. It adds 5,287 tokens to every session, about $0.0264 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.