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 LeekJay/claude-skills-plugin --skill git-operations-safetygit clone --depth 1 https://github.com/LeekJay/claude-skills-pluginWrote 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/leekjay/claude-skills-plugin/git-operations-safety)<a href="https://agentmods.dev/skills/leekjay/claude-skills-plugin/git-operations-safety"><img src="https://agentmods.dev/badge/skills/leekjay/claude-skills-plugin/git-operations-safety.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 5.1 | $0.00053 | $0.01648 |
| Opus 5 | $0.00026 | $0.00824 |
| Sonnet 5 | $0.00011 | $0.00330 |
| Haiku 4.5 | $0.00005 | $0.00165 |
Grade A, and why
git-operations-safety scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Operations Safety
Ensure Git operation safety and recoverability to prevent data loss.
Destructive Operations (Require Confirmation)
Following operations cause data loss or history changes, must get explicit user confirmation:
| Operation | Risk | Impact |
|---|---|---|
git reset --hard |
Lose all uncommitted changes | ⚠️ High risk - unrecoverable |
git push --force |
Overwrite remote history | ⚠️ High risk - affects team |
git clean -fd |
Delete untracked files | ⚠️ High risk - permanent deletion |
git branch -D |
Force delete branch | ⚠️ Medium risk - lose unmerged work |
Detailed Explanations
1. git reset --hard
Risk: Lose all uncommitted changes and staged content
Safe Alternatives:
# ✅ Use stash to save changes
git stash push -m "Temporary save"
git reset --hard HEAD
# If need to recover:
git stash pop
# ✅ Create backup branch
git branch backup-$(date +%Y%m%d-%H%M%S)
git reset --hard HEAD
Confirmation Process:
- Run
git statusto see what will be lost - Show user list of files that will be lost
- Ask: "This will lose following uncommitted changes, continue?"
- Only execute after explicit confirmation
2. git push --force
Risk: Overwrite remote history, affects other team members
Safe Alternative:
# ✅ Use --force-with-lease (safer)
git push --force-with-lease
Special Restrictions:
# ❌❌❌ Absolutely prohibit force push to main branch
git push --force origin main
git push --force origin master
# Must warn and require secondary confirmation
Warning Template:
🚨 Critical Warning:
You are attempting to force push to main branch, this is extremely dangerous!
Possible consequences:
- Overwrite other team members' commits
- Cause conflicts in team members' local repositories
- May lose important code changes
This operation should typically NOT be performed.
If you really need to do this:
1. Notify all team members
2. Confirm nobody is working based on main branch
3. Ensure complete backup exists
Do you really want to continue?
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.
- 8d ago First seen · 302 lines · 53 tokens per session scan A 582043c8cc8c
git-operations-safety is a skill published in the GitHub repository LeekJay/claude-skills-plugin (4 stars, last pushed 9mo ago), licensed MIT. It adds 53 tokens to every session and 1,648 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…