ccc-skill-create

ccc-skill-create is a command for Claude Code from KevinZai/commander. It costs 52 tokens per session (1,070 once invoked), scanned A, a copy of skill-create, MIT.

A command that studies a repository's Git history to identify recurring coding practices and generate SKILL.md instruction files.

In plain words
What is it for?
Use it to analyze commits, file changes, and commit-message habits, then create skills or optional learning instincts.
Why use it?
It turns patterns already used by a team into written guidance for Claude Code. This can make local conventions easier to reuse and teach.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions Codex.

Good fit Use it to analyze commits, file changes, and commit-message habits, then create skills or optional learning instincts.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kevinzai/commander/ccc-skill-create
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.

Clone the repo
git clone --depth 1 https://github.com/KevinZai/commander

Made for: Claude Code.

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 ccc-skill-create

README.md
[![agentmods](https://agentmods.dev/badge/commands/kevinzai/commander/ccc-skill-create/github.svg)](https://agentmods.dev/commands/kevinzai/commander/ccc-skill-create)
Your own site
<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-skill-create"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-skill-create/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ccc-skill-create

Your own site · 80×15
<a href="https://agentmods.dev/commands/kevinzai/commander/ccc-skill-create"><img src="https://agentmods.dev/badge/commands/kevinzai/commander/ccc-skill-create.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,070 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 95% 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 5.1 $0.00052 $0.01070
Opus 5.5 $0.00021 $0.00428
Sonnet 5.5 $0.00010 $0.00214
Haiku 4.5 $0.00005 $0.00107

Measured 6d ago against content hash 7c31ad883295, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ccc-skill-create 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.

Origin

This is a copy

95% identical to skill-create — 217 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.

commands/ccc-skill-create.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ccc-skill-create — a project skill from git history

CC Commander · /ccc-skill-create · a reviewed SKILL.md describing how this repository is actually worked on.

Arguments

$ARGUMENTS:

Flag Meaning
--commits <n> Commits to analyze (default 200)
--output <dir> Skills directory to write into (default .claude/skills)
--instincts Also write instincts for the continuous-learning-v2 system

What happens

  1. Confirm a git repository: git rev-parse --show-toplevel. If it fails, say so and stop. Use the top-level directory name as <repo-name>.

  2. Gather history (replace 200 with --commits):

    git log -n 200 --name-only --pretty=format:"%H|%s|%ad" --date=short
    git log -n 200 --name-only --pretty=format: | grep -v '^$' | sort | uniq -c | sort -rn | head -20
    git log -n 200 --pretty=format:%s | head -50
    

    If the repository has fewer commits than requested, analyze what exists and report the actual count.

  3. Detect patterns, each backed by evidence from step 2:

    Pattern How to detect
    Commit conventions Prefixes in subjects (feat:, fix:, chore:) and the share that follow them
    File co-changes Files that appear in the same commits repeatedly
    Workflow sequences Recurring sets of files changed for one kind of task
    Architecture Folder structure and naming, from git ls-files
    Testing Test file locations, naming, and the framework in the manifest

    Report a pattern only when it recurs; give its count (for example "41 of 50 subjects use conventional prefixes").

  4. Draft <output>/<repo-name>-patterns/SKILL.md in this shape:

    ---
    name: <repo-name>-patterns
    description: "Coding conventions and workflows used in <repo-name>. Use when writing commits, adding features or tests in this repository."
    metadata:
      source: local-git-analysis
      analyzed_commits: <n>
    ---
    
    # <Repo name> patterns
    
    ## Commit conventions
    ## Code architecture
    ## Workflows   (numbered steps per recurring task, with the exact files and commands)
    ## Testing patterns
    

Read the full file on GitHub · 106 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 Changed · -69 lines · +24 tokens per session 7c31ad883295
  2. 1mo ago First seen · 175 lines · 28 tokens per session scan A 0d0d60a3e3f8

Subscribe to this mod's changes

ccc-skill-create is a command published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,070 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 95% identical to skill-create, differing in 217 lines, and is treated as a copy.