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 Effulgent-Point/paw --skill git-safetygit clone --depth 1 https://github.com/Effulgent-Point/pawWrote 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/effulgent-point/paw/git-safety)<a href="https://agentmods.dev/skills/effulgent-point/paw/git-safety"><img src="https://agentmods.dev/badge/skills/effulgent-point/paw/git-safety/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/effulgent-point/paw/git-safety"><img src="https://agentmods.dev/badge/skills/effulgent-point/paw/git-safety.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 | $0.00000 | $0.00492 |
| Opus 5.5 | $0.00000 | $0.00197 |
| Sonnet 5.5 | $0.00000 | $0.00098 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
git-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 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.
What it actually says
Git Safety Skill
When to use: Any git operation that could lose work — pull, push, merge, rebase, branch management, conflict resolution.
Core doctrine
- Always pull (merge).
git pulldefaults to merge. Never use--rebase. - Never rebase published history. Rebase rewrites commits other people have cloned. Use merge.
- Never force-push.
--forceoverwrites remote history. Pull first, then push. - Never commit on main. Create a feature branch. Always.
Protected operations and alternatives
| Dangerous | Safe alternative |
|---|---|
git rebase main |
git pull origin main (merge) |
git pull --rebase |
git pull (merge) |
git push --force |
git pull origin branch && git push |
git branch -D feature |
git branch -d feature (safe delete) |
git reset --hard HEAD~1 |
git revert HEAD or git stash |
git checkout . |
git stash |
Conflict resolution
When merge conflicts happen:
- Understand both sides' intent — don't blindly pick "ours" or "theirs"
- Combine compatible changes — if both sides add different things, keep both
- Escalate competing changes — if both sides change the same logic differently, get both authors involved
- Run tests before committing the merge resolution
- If tests fail after resolution — escalate, don't guess
Branch workflow
- One branch per logical task
- Branch names:
feat/description,fix/description,chore/description - Delete branches after merge
- Keep branches short-lived — days, not weeks
Override escape hatches
For rare cases where you genuinely need the dangerous operation:
| Env var | Overrides |
|---|---|
PAW_ALLOW_REBASE=1 |
git rebase, git pull --rebase (local unpublished only) |
PAW_ALLOW_FORCE_PUSH=1 |
git push --force (never to main) |
Set the env var, run the command, unset. You can, but you have to mean it.
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 · 50 lines · 0 tokens per session scan A 578700b34ae5
git-safety is a skill published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 492 tokens. 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
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.
github
Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.
ship
Release pipeline for already-done local work. Dispatches /ground-state pre-flight, runs the project test suite, drafts a commit message, pushes, and opens a PR with a structured verification summary. Use when local changes are ready to hand off to review — e.g. 'ship this', 'push and open a PR', 'release this work'.…
uploads-cli
Reference for the uploads CLI and its stdio/hosted MCP tools — exact flags, keys, and contracts for put and attach, screenshot capture, stable PR/issue keys, the managed attachments comment, metadata and search, galleries, change feeds (repo-wide or one PR/issue), config defaults, login/doctor, and output formats. Use…
fix-pr
One-verb pipeline for the operator's highest-frequency manual loop: fetch a PR's unresolved reviewer feedback (inline review comments, review-summary bodies, and issue-level conversation comments) and failing CI checks, triage each issue via parallel read-only probes, fix the validated items in an isolated managed…