claude-code-framework AGENTS.md

Project instructions for claude-code-framework, a reusable collection of AI development workflows, commands, rules, hooks, agents, and templates. It explains the framework's structure and conventions for installing it into other projects.

In plain words
What is it for?
Use it when maintaining the framework, its agent and hook definitions, setup scripts, configuration, skills, templates, or CI files.
Why use it?
It prevents agents from treating the framework repository as an application project or changing files without following its synchronization and setup rules.

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/bostonorange/claude-code-framework/agents-md
Clone the repo
git clone --depth 1 https://github.com/BostonOrange/claude-code-framework

Made for: Codex, OpenCode.

Per session 4,141 This file is loaded in full into every session.
When invoked 4,141 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.04141 $0.04141
Opus 5 $0.02070 $0.02070
Sonnet 5 $0.00828 $0.00828
Haiku 4.5 $0.00414 $0.00414

Measured yesterday against content hash 5716c42b8a89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

claude-code-framework AGENTS.md scanned grade B with 1 finding 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -r "{{" .claude/ CLAUDE.md | grep -v ".git"
AGENTS.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Claude Code Framework

This file mirrors CLAUDE.md so that tools following the AGENTS.md convention (e.g. Codex) get the same framework instructions Claude Code does. Codex-format agent and hook configs live in .codex/; portable skills live in .agents/skills/. Keep this file and .codex/ in sync with CLAUDE.md and .claude/.

Project Overview

This is the claude-code-framework — a reusable AI development workflow framework. It provides skills, agents, commands, rules, hooks, and templates that get installed into target projects via setup.sh or setup.ps1.

This repo is the framework itself, NOT a target project. Do not run setup.sh here.

Tech Stack

Layer Technology
Skills Markdown (YAML frontmatter + instructions)
Agents Markdown (YAML frontmatter + multi-step processes)
Commands Markdown (YAML frontmatter + steps)
Rules Markdown (YAML frontmatter with patterns + guardrails)
Hooks Bash scripts
Setup Bash (setup.sh) + PowerShell (setup.ps1)
CI/CD templates GitHub Actions YAML
Config JSON (settings.json, settings.local.json)

System Structure

claude-code-framework/
├── CLAUDE.md                    # Claude Code instructions
├── AGENTS.md                    # This file (mirror of CLAUDE.md for AGENTS.md-convention tools)
├── README.md                    # User-facing documentation
├── setup.sh                     # Bash setup wizard
├── setup.ps1                    # PowerShell setup wizard
├── install-global-skill.sh      # Installs global skills into ~/.claude/skills/
├── install-global-skill.ps1     # PowerShell equivalent
├── global-skills/               # Account-level skills (→ ~/.claude/skills/), NOT per-repo
│   └── install-framework/       # /install-framework — bootstrap framework into any repo
├── .codex/                      # Codex-format configs for this repo (agents/*.toml, hooks/, hooks.json, config.toml)
├── .agents/skills/              # Portable skills for the AGENTS.md convention
├── templates/                   # Files copied to target projects
│   ├── CLAUDE.md.template       # Target project's CLAUDE.md
│   ├── settings.json            # User-level permissions (~/.claude/)
│   ├── settings.local.json      # Project-level permissions
│   ├── mcp.json                 # MCP server config (→ .mcp.json)
│   ├── agents/                  # 39 AI agent definitions
│   ├── commands/                # 11 quick command definitions
│   ├── internal-nextjs-business-app/ # Vendored app-creator template
│   ├── rules/                   # 23 file-pattern guardrails
│   ├── hooks/                   # 7 lifecycle scripts + 1 utility (codebase-index.sh)
│   └── statusline/              # Status bar config
├── skills/                      # 27 workflow skills + 1 template
├── workflows/                   # 4 GitHub Actions CI/CD templates
├── memory/                      # Memory system templates
└── docs/                        # Framework documentation

Read the full file on GitHub · 245 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. yesterday First seen · 245 lines · 4,141 tokens per session scan B 5716c42b8a89

Subscribe to this mod's changes

claude-code-framework AGENTS.md is an instructions file published in the GitHub repository BostonOrange/claude-code-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 4,141 tokens to every session, about $0.0207 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens