cannonball CLAUDE.md

cannonball CLAUDE.md is an instructions file for coding agents from harebeats/cannonball. It costs 596 tokens per session, scanned A, a copy of cannonball AGENTS.md, MIT.

Repository instructions for Cannonball, a collection of reusable agent skills and the Python engine that runs them. They explain where skills and data live and how to install and run them.

In plain words
What is it for?
Use them when operating in Cannonball to locate the skill collection, resolve its data directory, and run its Python scripts.
Why use it?
They help an agent find the correct files and use the project's portable, dependency-light setup correctly.

Instructions file

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/harebeats/cannonball/claude-md
Clone the repo
git clone --depth 1 https://github.com/harebeats/cannonball

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 cannonball CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/harebeats/cannonball/claude-md.svg)](https://agentmods.dev/instructions/harebeats/cannonball/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/harebeats/cannonball/claude-md"><img src="https://agentmods.dev/badge/instructions/harebeats/cannonball/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 596 This file is loaded in full into every session.
When invoked 596 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00596 $0.00596
Opus 5 $0.00298 $0.00298
Sonnet 5 $0.00119 $0.00119
Haiku 4.5 $0.00060 $0.00060

Measured 4d ago against content hash ff32b5b9e53c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cannonball 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.

Origin

This is a copy

100% identical to cannonball AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cannonball — para qualquer agente

Este repositório é um conjunto de Agent Skills mais o motor em Python que elas chamam. Ele não depende de nenhum agente específico.

O que você precisa saber para operar

Cada pasta em skills/ é autocontida. Ela traz o SKILL.md, o scripts/ que ele chama, o references/ que ele cita e o seed/ das peças de exemplo. Instalar uma skill é copiar a pasta dela; nada fica para trás.

Resolva o caminho pelo arquivo, não por variável. Todo comando nas skills usa ${SKILL_DIR}, que é a pasta do SKILL.md que você acabou de ler. Nenhuma variável de ambiente de agente é necessária — e é isso que faz o mesmo SKILL.md funcionar em Claude Code, Codex, Gemini CLI, Cursor e no resto.

Requisito único: Python 3. Os scripts importam só a biblioteca padrão. Sem pip install, sem node_modules, sem rede — exceto onde o próprio comando diz que usa rede (curar.py --assets testa URLs).

Onde ficam os dados

O acervo é do usuário e mora fora deste repositório. A resolução, em ordem:

  1. variável CANNONBALL_ACERVO
  2. cannonball.config.json na raiz, se a pasta existir
  3. ~/.cannonball/aonde — ponteiro escrito por scripts/vincular.py
  4. ../acervo relativo aos scripts, se você estiver rodando de um clone com dados
  5. ~/.cannonball — padrão, criado na hora com as peças de exemplo

Nunca grave acervo dentro da pasta da skill instalada: em vários hospedeiros ela é uma cópia em cache que a próxima atualização apaga.

A ordem que dá melhor resultado

vincular.py --para <pasta>  →  kit-ingerir  →  kit-buscar  →  kit-cor + kit-tipo
   →  kit-montar  →  kit-otimizar-3d  →  kit-ingerir (guarda o que deu certo)

python scripts/perfil.py imprime essa ordem já adaptada ao estado do acervo.

Ferramentas de agente citadas

As skills mencionam múltipla escolha para perguntas fechadas. Se o seu agente tiver uma ferramenta dessas, use; se não, pergunte em texto — nada quebra.

Quatro MCPs são opcionais e cada skill só dispara a seção correspondente quando o servidor está ligado: GetLayers, Motion Sites, OriginKit e Higgsfield. Nenhum é requisito.

Read the full file on GitHub · 51 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. 4d ago First seen · 51 lines · 596 tokens per session scan A ff32b5b9e53c

Subscribe to this mod's changes

cannonball CLAUDE.md is an instructions file published in the GitHub repository harebeats/cannonball (2 stars, last pushed 7d ago), licensed MIT. It adds 596 tokens to every session, about $0.0030 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cannonball AGENTS.md, differing in 0 lines, and is treated as a copy.

Related

Other instructions, from other repositories

naksha-studio copilot-instructions.md

Instructions for Adityaraj0421/naksha-studio, covering naksha design team — github copilot, activation triggers, the design team, design rules for code generation and css custom properties (always use these patterns).

Adityaraj0421/naksha-studio · 2,453 tokens

nextjs-admin-dashboard AGENTS.md

AGENTS.md instructions for NextAdminHQ/nextjs-admin-dashboard, covering nextadmin pro — ai agent rules, project structure, next.js, conventions and styling rules.

NextAdminHQ/nextjs-admin-dashboard · 985 tokens

stitch-kit AGENTS.md

Instructions for gabelul/stitch-kit, covering agents.md, what this repo is, skill structure, quick install (both platforms) and installing (claude code).

gabelul/stitch-kit · 1,673 tokens

fe-rail CLAUDE.md

Claude Code instructions for sh5623/fe-rail, covering fe-rail — claude 에이전트 컨텍스트, 이 저장소의 목적, 하네스 구조 (harness layers), 레이어별 역할 and 훅 프로파일 · 회귀 eval.

sh5623/fe-rail · 6,421 tokens

nextjs-admin-dashboard CLAUDE.md

Claude Code instructions for NextAdminHQ/nextjs-admin-dashboard, a project described as: AI-Native Next.js admin dashboard template and UI components that come with pre-built elements, components, pages, high-quality design, integrations, and much more.

NextAdminHQ/nextjs-admin-dashboard · 5 tokens

ui-ux-suite AGENTS.md

AGENTS.md instructions for Aboudjem/ui-ux-suite, covering agents.md: ui-ux-suite, what this tool is, how an ai agent should invoke it, preferred: the mcp tool uiuxauditrun and alternative: the cli.

Aboudjem/ui-ux-suite · 1,540 tokens