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 uchicago-dsi/ai-sci-skills --skill shared-checkout-gitgit clone --depth 1 https://github.com/uchicago-dsi/ai-sci-skillsWrote 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/uchicago-dsi/ai-sci-skills/shared-checkout-git)<a href="https://agentmods.dev/skills/uchicago-dsi/ai-sci-skills/shared-checkout-git"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/shared-checkout-git/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/uchicago-dsi/ai-sci-skills/shared-checkout-git"><img src="https://agentmods.dev/badge/skills/uchicago-dsi/ai-sci-skills/shared-checkout-git.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 | $0.00048 | $0.00711 |
| Opus 5.5 | $0.00019 | $0.00284 |
| Sonnet 5.5 | $0.00010 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
shared-checkout-git 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git In A Shared Checkout
The index is shared state. Two agents editing disjoint files are fine; two agents touching the index are not.
Give Each Bounded Change One Staging Owner
- Assign one explicit staging/commit owner per bounded change. Other agents may inspect or edit disjoint files, but they must not stage or commit while that owner is active.
- Immediately before staging, and again before committing, the owner must inspect the index and working tree, stage only the named paths, and stop if an unexpected staged path or an overlapping edit appears.
- Never use a shared
git add -A, amend another agent's commit, or reset the shared index to repair a collision. - A validation run across a populated index is a collision window, and the other owner's next commit will absorb whatever is sitting there.
Stage And Commit As One Action
git add followed by a separate git commit is two actions, and another owner's
commit can land between them however fast you are. That absorbed two agents' work
in one day, one of them a 417-line file that ended up inside an unrelated commit.
So either run validation before staging, or hold the change unstaged until the commit is issued:
git commit -- path/one path/two # index cannot decide what you commit
Enumerate Files, Never A Directory
A path-scoped commit takes the working-tree state of everything matching the
pathspec, so a directory in that pathspec silently widens the commit to every
modified file beneath it, including another owner's. git commit -- scripts/
intended to carry 21 files and carried 27: the extra six were a concurrent
owner's in-flight edits, which went from unstaged work in their tree to pinned
in someone else's commit. Their git status then reads clean, which is
misleading rather than reassuring, and the commit is not a valid execution pin
for either owner's change.
So enumerate the files. If the list is long enough to be tempting to collapse, that is a sign the change should be several commits.
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 · 70 lines · 48 tokens per session scan A bbf67bda4b69
shared-checkout-git is a skill published in the GitHub repository uchicago-dsi/ai-sci-skills (20 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 711 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 2026-09-22.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.