A repository caching workflow for remote Git repositories, which store and track source code. It keeps reusable local checkouts under a cache directory and refreshes them when needed.

Use it when a task refers to a GitHub, GitLab, or Bitbucket repository, so the repository can be cloned, reused, fetched, and fast-forwarded safely when possible.

It avoids repeatedly cloning the same repository while keeping the local reference reasonably up to date.

librarian — Skill for Claude Code and Codex by mitsuhiko: A repository caching workflow for remote Git repositories, which…

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/mitsuhiko/agent-stuff/librarian

Any agent

npx skills add mitsuhiko/agent-stuff --skill librarian

Clone the repo

git clone --depth 1 https://github.com/mitsuhiko/agent-stuff

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mitsuhiko/agent-stuff/librarian.svg)](https://agentmods.dev/skills/mitsuhiko/agent-stuff/librarian)

Your own site

<a href="https://agentmods.dev/skills/mitsuhiko/agent-stuff/librarian"><img src="https://agentmods.dev/badge/skills/mitsuhiko/agent-stuff/librarian.svg" alt="Measured on agentmods" height="20"></a>

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 499 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.

Model	Per session	Once invoked
Fable 5	$0.00057	$0.00499
Opus 5	$0.00028	$0.00249
Sonnet 5	$0.00011	$0.00100
Haiku 4.5	$0.00006	$0.00050

Measured 4d ago against content hash 40b60c3ba691, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

librarian 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 4d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (checkout.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/librarian/SKILL.md · 66 lines

What it actually says

Use this skill when the user points you to a remote git repository (GitHub/GitLab/Bitbucket URLs, git@..., or owner/repo shorthand).

The goal is to keep a reusable local checkout that is:

stable (predictable path)
up to date (periodic fetch + fast-forward when safe)
efficient (partial clone with --filter=blob:none, no repeated full clones)

Cache location

Repositories are stored at:

~/.cache/checkouts/<host>/<org>/<repo>

Example:

github.com/mitsuhiko/minijinja → ~/.cache/checkouts/github.com/mitsuhiko/minijinja

Command

bash checkout.sh <repo> --path-only

Examples:

bash checkout.sh mitsuhiko/minijinja --path-only
bash checkout.sh github.com/mitsuhiko/minijinja --path-only
bash checkout.sh https://github.com/mitsuhiko/minijinja --path-only

The script will:

Parse the repo reference into host/org/repo.
Clone if missing.
Reuse existing checkout if present.
Fetch from origin when stale (default interval: 300s).
Attempt a fast-forward merge if the checkout is clean and has an upstream.

Update strategy

Default behavior is throttled refresh (every 5 minutes) to avoid unnecessary network calls.
Force immediate refresh with:

bash checkout.sh <repo> --force-update --path-only

Recommended workflow

Resolve repository path via checkout.sh --path-only.
Use that path for searching, reading, and analysis.
On later references to the same repo, call checkout.sh again; it will find and update the cached checkout.

If edits are needed

Prefer not to edit directly in the shared cache. Create a separate worktree or copy from the cached checkout for task-specific modifications.

Notes

owner/repo defaults to github.com.

Files

What ships with it

1 file 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.

checkout.sh 6.3 KB runs code

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.

4d ago First seen · 66 lines · 57 tokens per session scan A 40b60c3ba691

Subscribe to this mod's changes

librarian is a skill published in the GitHub repository mitsuhiko/agent-stuff (3,044 stars, last pushed 2d ago), licensed Apache-2.0. It adds 57 tokens to every session and 499 once invoked, about $0.0003 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.

Git and workflow Productivity

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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