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/yale-som-hpc/claude-code-marketplace/using-git-and-githubnpx skills add yale-som-hpc/claude-code-marketplace --skill using-git-and-githubgit clone --depth 1 https://github.com/yale-som-hpc/claude-code-marketplaceWrote 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/yale-som-hpc/claude-code-marketplace/using-git-and-github)<a href="https://agentmods.dev/skills/yale-som-hpc/claude-code-marketplace/using-git-and-github"><img src="https://agentmods.dev/badge/skills/yale-som-hpc/claude-code-marketplace/using-git-and-github.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.01101 |
| Opus 5 | $0.00034 | $0.00550 |
| Sonnet 5 | $0.00014 | $0.00220 |
| Haiku 4.5 | $0.00007 | $0.00110 |
Grade A, and why
using-git-and-github 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 5d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Git and GitHub
For agents helping researchers get version-control benefits without becoming git experts.
Rules
- Track code, config, metadata, docs, lockfiles, small examples.
- Do not track raw data, secrets, env dirs, package libraries, large generated outputs.
- Commit logical checkpoints.
- Prefer simple history. No force-push on shared branches unless explicitly approved.
- Explain git decisions plainly.
Git on HPC
Git may require a module:
module load git
git --version
Use module load git in setup notes/scripts that need git on HPC.
Auth and pushing
Laptop: HTTPS with gh auth login or normal SSH keys are fine.
HPC: prefer SSH agent forwarding so private keys stay on the laptop:
ssh -A hpc
module load git
ssh -T [email protected]
git push
If SSH_AUTH_SOCK is stale, fix the socket pointer. Do not copy private keys to the cluster. See connecting securely.
HTTPS / gh token auth is also fine if already configured:
module load git
gh auth status
git push
Never copy ~/.ssh/id_* private keys onto the cluster. Public keys (*.pub) are safe; private keys are not.
Agent behavior
- Run
git status --shortbefore and after edits. - Do not silently stage ambiguous untracked files. Report and propose track/ignore/refuse.
- Commit when asked, or when a coherent requested task is complete and repo norms expect commits. If uncertain, ask once.
- Use imperative messages:
Add panel construction script,Fix Slurm memory request. - Report hash + summary.
Track / ignore
Track:
- source, scripts, Slurm scripts,
- README/docs,
pyproject.toml,uv.lock,renv.lock,.Rprofile,- small metadata/codebooks/config,
- tiny synthetic fixtures,
- Makefiles/justfiles.
Ignore:
# Data and outputs
data/raw/
data/derived/
output/
outputs/
results/
logs/
*.parquet
*.rds
*.RDS
*.dta
*.sas7bdat
*.feather
*.h5
*.h5ad
# Python
.venv/
__pycache__/
*.pyc
.pytest_cache/
.ruff_cache/
# R
.Rhistory
.RData
.Rproj.user/
renv/library/
renv/local/
renv/staging/
# Secrets / local config
.env
.env.local
*.pem
*.key
# OS/editor
.DS_Store
Thumbs.db
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.
- 5d ago First seen · 185 lines · 68 tokens per session scan A b7e6a38046c4
using-git-and-github is a skill published in the GitHub repository yale-som-hpc/claude-code-marketplace (5 stars, last pushed 1mo ago), licensed Unlicense. It adds 68 tokens to every session and 1,101 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 2026-08-31.
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-next. 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.
commit-push-pr
Commit selected local changes, push the branch, and create or update a GitHub pull request with BitFun attribution. Use when the user asks to 提交 PR、提代码、commit and push、开 PR、create a pull request, or wants a Claude Code-like one-command PR publishing flow from BitFun.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
commit
Commit current changes with a clear, descriptive message.
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…