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.
npx agentmods add skills/recca0120/code-quest/simple-git-referencenpx skills add recca0120/code-quest --skill simple-git-referencegit clone --depth 1 https://github.com/recca0120/code-questWhat 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 | $0.00000 | $0.00783 |
| Opus 5 | $0.00000 | $0.00392 |
| Sonnet 5 | $0.00000 | $0.00157 |
| Haiku 4.5 | $0.00000 | $0.00078 |
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 2d 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.
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);
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.
- 2d ago First seen · 102 lines · 0 tokens per session scan A c3e7290a422a
simple-git-reference is a skill published in the GitHub repository recca0120/code-quest (11 stars, last pushed 2mo 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…