bundles-forge CLAUDE.md

bundles-forge CLAUDE.md is an instructions file for coding agents from OdradekAI/bundles-forge. It costs 1,848 tokens per session, scanned A, original, Apache-2.0.

A guide for Bundles Forge, a toolkit that develops add-on bundles for Claude Code, Cursor, Codex, OpenCode, Gemini CLI, and OpenClaw.

In plain words
What is it for?
Use it to run the test suites, inspect integration behavior, validate scripts, and maintain the toolkit’s bundle-plugin lifecycle.
Why use it?
It explains the project’s purpose, Python requirements, testing commands, and quality checks for its eight development skills.

Instructions file

Installs and runs on its own, but its text points at files inside the plugin that ships it — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed.

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/odradekai/bundles-forge/claude-md
Clone the repo
git clone --depth 1 https://github.com/OdradekAI/bundles-forge

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 bundles-forge CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/odradekai/bundles-forge/claude-md.svg)](https://agentmods.dev/instructions/odradekai/bundles-forge/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/odradekai/bundles-forge/claude-md"><img src="https://agentmods.dev/badge/instructions/odradekai/bundles-forge/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,848 This file is loaded in full into every session.
When invoked 1,848 The same file — it is already loaded in full.
Security scan A 2 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 $0.01848 $0.01848
Opus 5 $0.00924 $0.00924
Sonnet 5 $0.00370 $0.00370
Haiku 4.5 $0.00185 $0.00185

Measured 5d ago against content hash 096e77247b15, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bundles-forge CLAUDE.md scanned grade A with 2 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- No network calls (`curl`, `wget`) in hook scripts

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- No `eval()` or `child_process` in plugin code
CLAUDE.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 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.

Project Overview

Bundles Forge is a bundle-plugin engineering toolkit supporting 6 platforms: Claude Code, Cursor, Codex, OpenCode, Gemini CLI, and OpenClaw. It contains 8 skills covering the full lifecycle of bundle-plugin development (design, scaffold, author, audit, test, optimize, release). The project itself is a bundle-plugin — it uses its own patterns to build and validate itself.

Requires Python 3.9+ (scripts use pathlib.Path.is_relative_to and other 3.9+ features).

Commands

Testing

python tests/run_all.py                            # all 6 test suites (scripts, integration, graph fixtures, unit, skill quality, workflow chains)
python tests/test_scripts.py -v                    # auditing/releasing script tests (unittest)
python tests/test_integration.py -v                # structure, hooks, version sync, skill discovery
python -m pytest tests/test_scripts.py -v          # same, via pytest
python -m pytest tests/test_scripts.py -v -k test_project_mode_runs_without_error  # single test

Test suites: test_scripts (audit/release CLI scripts), test_integration (project structure, hooks, version sync, skill discovery), test_graph_fixtures (dependency graph fixtures), test_unit (unit tests), test_skill_quality (description format, cross-references, Integration symmetry), test_workflow_chains (live project workflow integrity, Calls/Called-by symmetry, graph connectivity). All 6 are collected by tests/run_all.py.

Quality & Security

bundles-forge audit-skill [target-dir]       # project-level skill quality audit (auto-detects mode)
bundles-forge audit-skill [skill-dir]          # single skill audit (4 categories)
bundles-forge audit-skill --all [target-dir] # force project-level mode
bundles-forge audit-security [target-dir]     # 7-surface security scan
bundles-forge audit-plugin [target-dir]     # combined audit (calls audit_skill + audit_security + workflow)
bundles-forge audit-workflow [target-dir]    # workflow integration audit (W1-W11)
bundles-forge audit-docs [target-dir]        # documentation consistency (9 checks: D1-D9)
bundles-forge checklists [target-dir]        # regenerate checklist tables from audit-checks.json registry
bundles-forge checklists --check [target-dir] # detect checklist drift (exit 1 if stale)

Read the full file on GitHub · 114 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. 5d ago First seen · 114 lines · 1,848 tokens per session scan A 096e77247b15

Subscribe to this mod's changes

bundles-forge CLAUDE.md is an instructions file published in the GitHub repository OdradekAI/bundles-forge (230 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,848 tokens to every session, about $0.0092 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.