Claude Code From Scratch is a step-by-step learning project that recreates the core architecture of a coding agent in roughly 5,000 lines of TypeScript and Python. It is for developers who want to understand how coding agents work without reading a much larger codebase.
Borrowing it
Nothing to install: this file belongs to Windy3f3f3f3f/claude-code-from-scratch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Windy3f3f3f3f/claude-code-from-scratch/main/.claude/skills/commit/SKILL.mdgit clone --depth 1 https://github.com/Windy3f3f3f3f/claude-code-from-scratchWrote 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.
[](https://agentmods.dev/skills/windy3f3f3f3f/claude-code-from-scratch/commit)<a href="https://agentmods.dev/skills/windy3f3f3f3f/claude-code-from-scratch/commit"><img src="https://agentmods.dev/badge/skills/windy3f3f3f3f/claude-code-from-scratch/commit/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.
<a href="https://agentmods.dev/skills/windy3f3f3f3f/claude-code-from-scratch/commit"><img src="https://agentmods.dev/badge/skills/windy3f3f3f3f/claude-code-from-scratch/commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00011 | $0.00105 |
| Opus 5.5 | $0.00004 | $0.00042 |
| Sonnet 5.5 | $0.00002 | $0.00021 |
| Haiku 4.5 | $0.00001 | $0.00011 |
Grade A, and why
commit 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 1mo 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.
What it actually says
Commit Skill
- Run
git diff --stagedandgit statusto see what's changed - Write a concise commit message summarizing the changes
- Run
git commit -m "<message>"
If no files are staged, tell the user to stage files first. Arguments passed to this skill are used as additional context for the commit message.
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.
- 1mo ago First seen · 16 lines · 11 tokens per session scan A f366107fe9d3
commit is a skill published in the GitHub repository Windy3f3f3f3f/claude-code-from-scratch (2,797 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 105 once invoked, about $0.0000 per session on Opus 5.5. 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.
Other skills, from other repositories
caveman-commit
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
git
Source-control safety for Git. Two rules apply whether or not you read the body. First, never commit, amend, push, tag, rebase, cherry-pick, revert, or reset --hard unless the user asked for that exact write in this session. An explicit request to create a new commit counts anywhere in the user's own task text, but it…
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
changelog
Auto-generate a changelog from git commits and sprint data. Internal and player-facing versions.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
install-skill
Install a community skill pack into this fork from a GitHub repo and ship it as an auto-merged PR.