c3

c3 is a skill for Claude Code from lagz0ne/c3-skill. It costs 135 tokens per session (2,620 once invoked), scanned A, original, MIT.

An architecture-management add-on built around C3, a project-specific model of the system's facts and relationships. It freezes shared facts and requires approved change units—an architecture decision plus its related patch—to modify them.

In plain words
What is it for?
Mapping a domain, recording and freezing architecture facts, making reviewed changes, and safely expanding or reshaping the model.
Why use it?
It provides a controlled way to keep architecture documentation and implementation changes consistent as the system evolves.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the c3-skill plugin — 2 skills, 2 commands shipped together

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 skills/lagz0ne/c3-skill/c3
Any agent
npx skills add lagz0ne/c3-skill --skill c3
Clone the repo
git clone --depth 1 https://github.com/lagz0ne/c3-skill

Made for: Claude Code.

Or install c3-skill, the plugin that ships this one along with the rest of its 2 skills, 2 commands.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/lagz0ne/c3-skill/c3.svg)](https://agentmods.dev/skills/lagz0ne/c3-skill/c3)
Your own site
<a href="https://agentmods.dev/skills/lagz0ne/c3-skill/c3"><img src="https://agentmods.dev/badge/skills/lagz0ne/c3-skill/c3.svg" alt="Measured on agentmods" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,620 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00135 $0.02620
Opus 5 $0.00068 $0.01310
Sonnet 5 $0.00027 $0.00524
Haiku 4.5 $0.00014 $0.00262

Measured 6d ago against content hash 1ef31875f82d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

c3 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.

The scan reads SKILL.md. This mod also ships 1 executable file (bin/c3x.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/c3/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

C3 — one model, three acts

C3 is your architecture's own vocabulary, frozen into shared truth, that work edits only through reviewed change-units.

  1. Shape the model, freeze the facts. Descend the domain top-down — draft the facts the work needs and wire them as you go; the lean canvas (sections + typed columns each entity carries here) is already in place, taking a custom fact-type only where the domain needs one. Then flip the gate and the facts freeze: shared truth, never hand-edited again.
  2. Change-units drive progress. Work advances by change-units — an ADR plus its patch folder, one atomic saga: declare intent, the tool keeps the result integral (membership, citations, gates), flip it all-or-nothing. Frozen facts change only through this merge.
  3. The canvas grows — and evolves — with the need. When work outgrows the model, raise the canvas (climb a rung, additive) or morph it (reshape a mis-modeled type non-additively) and migrate every fact to fit — in one gated, atomic unit; completeness is never relaxed.

Build the model → freeze the facts → change-units drive the work → the canvas grows with the need.

CLI invocation

The packaged runtime is c3x, exposed through the skill-local wrapper at <skill-dir>/bin/c3x.sh. There is no c3 executable. Invoke the wrapper explicitly for every command:

# Template: resolve <skill-dir> to this skill's directory, then replace the command and args.
C3X_MODE=agent bash "<skill-dir>/bin/c3x.sh" check

For several commands in one shell, this helper is allowed, but it is only a shell function and does not install a c3 command:

c3local() { C3X_MODE=agent bash "<skill-dir>/bin/c3x.sh" "$@"; }

C3X_MODE=agent → TOON output (~40% fewer tokens) and help[] hints appended to each result — follow them. The packaged CLI is the single source; this skill is the router: classify the intent, load the reference, invoke the wrapper, follow the output. It names every gate and teaches no procedure — procedure lives in the references.

Read the full file on GitHub · 97 lines

Files

What ships with it

12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 97 lines · 135 tokens per session scan A 1ef31875f82d

Subscribe to this mod's changes

c3 is a skill published in the GitHub repository lagz0ne/c3-skill (12 stars, last pushed 1mo ago), licensed MIT. It adds 135 tokens to every session and 2,620 once invoked, about $0.0007 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens