agentmods.dev

ai-tools CLAUDE.md

ai-tools CLAUDE.md is an instructions file for coding agents from bang9/ai-tools. It costs 1,497 tokens per session, scanned C, original, MIT.

Repository instructions for a collection of separate Claude Code tools, including rules for shared code, compiled binaries, supported platforms, versions, and releases.

In plain words
What is it for?
Developing tools, preparing binaries for macOS, Linux, and Windows, managing versions, and following the shared release process.
Why use it?
It gives contributors consistent development and release requirements across the tool modules.

Instructions file

not rated 10 1mo ago C scan 1,497 tokens original MIT
View the source file bang9/ai-tools
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/bang9/ai-tools/claude-md
Clone the repo
git clone --depth 1 https://github.com/bang9/ai-tools

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 ai-tools CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bang9/ai-tools/claude-md.svg)](https://agentmods.dev/instructions/bang9/ai-tools/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bang9/ai-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/bang9/ai-tools/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,497 This file is loaded in full into every session.
When invoked 1,497 The same file — it is already loaded in full.
Security scan C 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 $0.01497 $0.01497
Opus 5 $0.00749 $0.00749
Sonnet 5 $0.00299 $0.00299
Haiku 4.5 $0.00150 $0.00150

Measured 5d ago against content hash 651e562c1a9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

ai-tools CLAUDE.md scanned grade C 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

├── install.sh # One-liner install script (curl | bash)

Makes network callslowCapability

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

├── install.sh # One-liner install script (curl | bash)
CLAUDE.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ai-tools Development Guidelines

Project Overview

This repository contains tools for Claude Code to operate more efficiently. Each tool is a separate module under its own directory. Cross-tool shared code lives under shared/ and should stay domain-neutral instead of absorbing tool-specific workflows.

Release Policy

Binary Distribution

All tools with compiled binaries MUST provide pre-built binaries for users without build tools installed.

Supported Platforms:

  • darwin-arm64 (macOS Apple Silicon)
  • darwin-amd64 (macOS Intel)
  • linux-amd64 (Linux x86_64)
  • windows-amd64 (Windows x86_64)

Version Management

  • Tag format: v<MAJOR>.<MINOR>.<PATCH> (e.g., v1.2.0)
  • All tools share the same version and are released together
  • ensure-binary.sh and install.sh fetch the latest version from GitHub API
  • Plugin version fields are auto-updated by CI on release

Release Process

  1. Commit changes
  2. Create and push tag: git tag v1.x.x && git push --tags
  3. release.yml orchestrates:
    • N product workflows build binaries and attach to GitHub Release
    • cc-marketplace-release.yml updates plugin.json versions + regenerates marketplace.json + auto-commits to main

CI/CD

Workflow Structure

.github/workflows/
├── release.yml                  # Orchestrator (tag v* trigger)
├── <tool>-release.yml           # Product build (reusable, called by release.yml)
├── cc-marketplace-release.yml   # Version + marketplace sync (reusable, called by release.yml)
├── <tool>-test.yml              # Test workflow (push to main + PRs, path-filtered)
└── .github/scripts/
    └── sync-marketplace.sh      # Generates marketplace.json from plugin.json files

Orchestrator (release.yml):

  • Triggers on tag push matching v*
  • Calls all <tool>-release.yml workflows in parallel
  • Then calls cc-marketplace-release.yml to sync versions

Product release (<tool>-release.yml):

  • Triggered via workflow_call with version input
  • Builds cross-platform binaries and attaches to GitHub Release

Read the full file on GitHub · 146 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 · 146 lines · 1,497 tokens per session scan C 651e562c1a9f

Subscribe to this mod's changes

ai-tools CLAUDE.md is an instructions file published in the GitHub repository bang9/ai-tools (10 stars, last pushed 1mo ago), licensed MIT. It adds 1,497 tokens to every session, about $0.0075 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

ai-agentclaude-codecodextask-managertask-orchestration
Related

Other instructions, from other repositories

Backlog.md AGENTS.md

AGENTS.md instructions for MrLesk/Backlog.md, covering read this first, simplicity-first implementation rules, ui descriptions, commands and development.

MrLesk/Backlog.md · 1,637 tokens

Backlog.md copilot-instructions.md

Copilot instructions for MrLesk/Backlog.md, covering ⚠️ important, commands, development, testing and configuration management.

MrLesk/Backlog.md · 467 tokens

agentrq AGENTS.md

AGENTS.md instructions for agentrq/agentrq, covering agentrq codebase notes, project layout, desktop app (desktop/), three traps that are invisible in source and running tests.

agentrq/agentrq · 1,561 tokens

vibe-kanban AGENTS.md

Instructions for BloopAI/vibe-kanban, covering repository guidelines, project structure & module organization, crate-specific guides, managing shared types between rust and typescript and build, test, and development commands.

BloopAI/vibe-kanban · 1,005 tokens

DaybydayCRM AGENTS.md

AGENTS.md instructions for Bottelet/DaybydayCRM, covering daybydaycrm agent guide, documentation map, project snapshot, architecture rules and keep controllers thin.

Bottelet/DaybydayCRM · 999 tokens

DaybydayCRM copilot-instructions.md

Copilot instructions for Bottelet/DaybydayCRM, covering copilot instructions for daybydaycrm, working defaults, testing defaults, repository patterns to respect and known pitfalls.

Bottelet/DaybydayCRM · 633 tokens