c3-skill CLAUDE.md

c3-skill CLAUDE.md is an instructions file for Claude Code, Codex from lagz0ne/c3-skill. It costs 1,807 tokens per session, scanned A, original, MIT.

A set of development instructions for C3, a Go command-line tool and Claude skill. It explains how to work on the local repository and where the product's operation rules are documented.

In plain words
What is it for?
Use it when developing or debugging C3, following its change-unit, freeze, and canvas model, or preparing its plugin and skill for release.
Why use it?
It prevents agents from accidentally using a different installed version of C3 and defines the commands and files to use for this checkout.

Instructions file for Claude CodeCodex

Written for Claude Code and Codex: Claude Code plugin machinery, but also reads ~/.codex or $CODEX_HOME. Also seen: reads .claude/ paths; mentions subagents; mentions Codex.

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/lagz0ne/c3-skill/claude-md
Clone the repo
git clone --depth 1 https://github.com/lagz0ne/c3-skill

Made for: Claude Code, Codex.

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 c3-skill CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lagz0ne/c3-skill/claude-md.svg)](https://agentmods.dev/instructions/lagz0ne/c3-skill/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lagz0ne/c3-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/lagz0ne/c3-skill/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,807 This file is loaded in full into every session.
When invoked 1,807 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 5.1 $0.01807 $0.01807
Opus 5 $0.00903 $0.00903
Sonnet 5 $0.00361 $0.00361
Haiku 4.5 $0.00181 $0.00181

Measured 6d ago against content hash 3ddbc2bdf31a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

c3-skill 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 6d 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.

CLAUDE.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working in this repo

This is the C3 product source — the Go CLI and the Claude skill that ships it. This file is the repo-dev contract: how to invoke C3 here, how we work, and how we release. It teaches no product behavior.

What C3 is, the operation set, and the change-unit / freeze / canvas model are owned by skills/c3/SKILL.md. Read it there; do not duplicate it here.


Local C3 Source Rule

This repository is the C3 project source. Work here is intentionally outside the installed/global C3 skill scope — never let the global skill answer for this checkout.

Hard rules:

  • Do not use bare c3x; it may resolve to the global installed skill.
  • Do not load C3 from ~/.agents/skills/c3, ~/.claude/skills/c3, ~/.codex/skills/c3, or marketplace installs for this repo.
  • Load C3 skill instructions from skills/c3/SKILL.md in this checkout.
  • Run C3 through the local built wrapper: C3X_MODE=agent bash skills/c3/bin/c3x.sh <command>.
  • If skills/c3/bin/c3x.sh or the matching local binary is missing, tell the user — CI builds binaries, not you. Only run bash scripts/build.sh when explicitly debugging the build.
  • The wrapper rebuilds only when the platform binary is absent; after editing CLI source, delete the stale gitignored binary in skills/c3/bin/ so you don't dogfood old code.
  • At session start, create a local alias/function and use it for every C3 command:
alias c3local='C3X_MODE=agent bash skills/c3/bin/c3x.sh'
c3local check

If C3 output looks wrong, commands fail unexpectedly, or behavior differs from source changes, suspect the wrong C3 version is being used. Prove the path/version before continuing.

File lookup: c3local lookup <file-or-glob> maps files/directories to components + refs. CLI: c3local <command> after the alias above; see skills/c3/SKILL.md for the operation set.


Workflow

  • Load /superpowers:brainstorming and /superpowers-developing-for-claude-code:developing-claude-code-plugins up front.
  • Use AskUserQuestionTool where possible — it yields a better-grounded answer.
  • Start with brainstorming to pin the intention; align the concept in prose before offering implementation menus.
  • Once understood, write the plan, then implement in parallel using subagents.
  • Before claiming work is done: run /noslop to strip AI slop, then run the local C3 flow (c3local check for doc integrity + c3local eval for fact↔code conformance) to verify docs match code.
  • Delegate to /release when done; confirm scope with the user. Patch by default.

Read the full file on GitHub · 132 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. 6d ago First seen · 132 lines · 1,807 tokens per session scan A 3ddbc2bdf31a

Subscribe to this mod's changes

c3-skill CLAUDE.md is an instructions file published in the GitHub repository lagz0ne/c3-skill (12 stars, last pushed 1mo ago), licensed MIT. It adds 1,807 tokens to every session, about $0.0090 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 2026-08-30.

Related

Other instructions, from other repositories

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

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 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

next.js AGENTS.md

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

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 · 4,469 tokens