code-quest: Skill for Claude Code

.claude/skills/simple-git-reference/SKILL.md

simple-git-reference is a skill for Claude Code from recca0120/code-quest. It costs 0 tokens per session (783 once invoked), scanned A, original, MIT.

A reference for simple-git, a TypeScript library that runs Git operations from code. It covers repository instances, status, history, changes, branches, worktrees, errors, and types.

In plain words
What is it for?
Use it when building code that checks repositories, reads logs or diffs, switches branches, finds repository roots, or runs Git commands such as creating worktrees.
Why use it?
It helps developers use Git programmatically without guessing method names, return values, or repository-instance setup. It also highlights details such as limiting history queries and avoiding conflicts between instances.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is recca0120/code-quest's own configuration. It tells Claude Code how to work on code-quest itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything code-quest configures →

Reuse

Borrowing it

Nothing to install: this file belongs to recca0120/code-quest. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/recca0120/code-quest/main/.claude/skills/simple-git-reference/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/recca0120/code-quest

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 simple-git-reference

README.md
[![agentmods](https://agentmods.dev/badge/skills/recca0120/code-quest/simple-git-reference/github.svg)](https://agentmods.dev/skills/recca0120/code-quest/simple-git-reference)
Your own site
<a href="https://agentmods.dev/skills/recca0120/code-quest/simple-git-reference"><img src="https://agentmods.dev/badge/skills/recca0120/code-quest/simple-git-reference/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 simple-git-reference

Your own site · 80×15
<a href="https://agentmods.dev/skills/recca0120/code-quest/simple-git-reference"><img src="https://agentmods.dev/badge/skills/recca0120/code-quest/simple-git-reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 783 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 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 $0.00000 $0.00783
Opus 5.5 $0.00000 $0.00313
Sonnet 5.5 $0.00000 $0.00157
Haiku 4.5 $0.00000 $0.00078

Measured 2mo ago against content hash c3e7290a422a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

simple-git-reference 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 2mo 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/skills/simple-git-reference/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

simple-git Reference

Instance

import simpleGit, { SimpleGit } from 'simple-git';

// Per-repo instance (lightweight, has internal task queue)
const git: SimpleGit = simpleGit({ baseDir: cwd, trimmed: true });
  • 一個 instance per repo cwd(不需要 singleton)
  • maxConcurrentProcesses 預設 5,多 instance 同 repo 可能 lock contention

API

// status
const s = await git.status();
// s.current — branch name | null (detached)
// s.isClean() — boolean
// s.files — Array<{ path, index, working_dir }>  (status codes: M, A, D, ?, !)

// log
const l = await git.log({ maxCount: 20 });
// l.all — Array<{ hash, date, message, author_name, author_email }>
// ⚠️ 沒有 maxCount 會撈全部 history

// diff
const d = await git.diff();              // unstaged changes (string)
const d2 = await git.diff(['--cached']); // staged
// diff() 回傳 string,要結構化用 diffSummary()

// checkout
await git.checkout('branch');
// fetch + checkout fallback:
await git.fetch('origin', branch).then(() => git.checkout(branch));

// revparse
const root = await git.revparse(['--show-toplevel']);

// raw — 任何沒有專用 method 的操作
await git.raw(['worktree', 'add', '-b', branch, path, base]);
await git.raw(['worktree', 'list', '--porcelain']);
await git.raw(['worktree', 'remove', path]);
await git.raw(['symbolic-ref', 'refs/remotes/origin/HEAD']);

Error Handling

import { GitError } from 'simple-git';

try {
  await git.checkout('nonexistent');
} catch (e) {
  if (e instanceof GitError) {
    // e.message — stderr text
  }
}
  • 大多數失敗丟 GitError
  • GitResponseError 只在 git exit 0 但 parsed response 有問題時出現(如 merge conflict)

TypeScript Types

Package 自帶 types:SimpleGit, StatusResult, LogResult, DefaultLogFields, GitError, SimpleGitOptions

Testing

// 用 DI:wrap simple-git 在 thin service,注入 mock
// 或 vi.mock:
import simpleGit from 'simple-git';
vi.mock('simple-git');

const mockGit = {
  status: vi.fn().mockResolvedValue({ current: 'main', isClean: () => true, files: [] }),
  log: vi.fn().mockResolvedValue({ all: [], latest: null }),
  diff: vi.fn().mockResolvedValue(''),
  raw: vi.fn().mockResolvedValue(''),
};
vi.mocked(simpleGit).mockReturnValue(mockGit as any);

Read the full file on GitHub · 102 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. 2mo ago First seen · 102 lines · 0 tokens per session scan A c3e7290a422a

Subscribe to this mod's changes

simple-git-reference is a skill published in the GitHub repository recca0120/code-quest (11 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 783 tokens. 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.