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 skills add aiya000/dotfiles --skill git-fetchgit clone --depth 1 https://github.com/aiya000/dotfilesWrote 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/aiya000/dotfiles/git-fetch)<a href="https://agentmods.dev/skills/aiya000/dotfiles/git-fetch"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/git-fetch/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/aiya000/dotfiles/git-fetch"><img src="https://agentmods.dev/badge/skills/aiya000/dotfiles/git-fetch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00041 | $0.00575 |
| Opus 5.5 | $0.00016 | $0.00230 |
| Sonnet 5.5 | $0.00008 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
git-fetch 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 18d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
git-fetch
Fetch commits from remote and report what is incoming. The working tree and the local branches stay as they are.
Behavior
- Run
git statusto check the current branch and its upstream - Run
git fetchfor the upstream remote - Inspect the incoming and outgoing commits (see Inspecting Incoming Commits below)
- Report the result (see Report below)
Inspecting Incoming Commits
After fetching, compare the local branch with its upstream:
git rev-list --left-right --count HEAD...@{u}-- the number of outgoing (left) and incoming (right) commitsgit log --oneline HEAD..@{u}-- the incoming commitsgit diff --stat HEAD...@{u}-- the files the incoming commits touch
Point out anything in the incoming changes that runs code or changes how tools behave, since pulling
would apply it silently: git hooks, .envrc, shell rc files, package.json scripts, Makefile, CI
workflows, Claude Code settings or hooks.
Report
Report these, so the caller (the user, or the git-pull skill) can decide what to do next:
- The state of the branch against its upstream: up to date, behind (only incoming commits, fast-forward possible), ahead (only outgoing commits), or diverged (both)
- The incoming commits and the files they touch
- Any incoming change that runs code or changes how tools behave
Does Not
- Merge, rebase, or otherwise change the local branches or the working tree
- Run
git fetch --pruneor delete remote-tracking branches without explicit user request - Fetch with a refspec that overwrites local branches (e.g.
git fetch origin main:main) without explicit user request
Notes
- If the current branch has no upstream, or it is uncertain which remote to fetch from, ask the user
before running
git fetch - If
git fetchfails withcould not lock config file .git/configinside the sandbox, rerun it withdangerouslyDisableSandbox: true(see the "Phantom Dotfiles in the Sandbox" section of the global config)
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.
- 18d ago First seen · 51 lines · 41 tokens per session scan A 9b8aee19912f
git-fetch is a skill published in the GitHub repository aiya000/dotfiles (21 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 575 once invoked, about $0.0002 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 2026-09-28.
Other skills, from other repositories
restart__pull_request
A pull-request restart workflow for replacing a messy review with a new pull request containing one clean commit and a summary of the earlier discussion.
rescue__pull_request_review
An automated workflow for handling GitHub pull-request review comments, applying requested code changes, committing them, and pushing them back.
submit__pull_request
An automated pull-request submission workflow. A pull request is a request for a code change to be reviewed and merged; this workflow writes its explanation, creates it, watches its automated checks, and fixes failed checks.
write__pull_request
A workflow for writing a pull request description, the explanation attached to a proposed code change for review. It analyses the changes and commit history.
monitor__ci_status
An automated monitor for GitHub Actions, the service that runs checks such as tests after code changes. It watches all checks after a pull request or a push to a pull-request branch and can invoke a failure-recovery process.
monitor__pull_request_conflict
An automated check for GitHub pull requests, which are proposed code changes awaiting review or merging.