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/basher83/lunar-claude/git-opsnpx skills add basher83/lunar-claude --skill git-opsgit clone --depth 1 https://github.com/basher83/lunar-claudeWrote 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/basher83/lunar-claude/git-ops)<a href="https://agentmods.dev/skills/basher83/lunar-claude/git-ops"><img src="https://agentmods.dev/badge/skills/basher83/lunar-claude/git-ops.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 | $0.00109 | $0.01642 |
| Opus 5 | $0.00055 | $0.00821 |
| Sonnet 5 | $0.00022 | $0.00328 |
| Haiku 4.5 | $0.00011 | $0.00164 |
Grade A, and why
git-ops 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 2d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Ops (router)
The single front door for all git operations in this repo. The user is Blake — not a developer, so expect plain language, not "commit", "push", or "merge". For every request:
- Translate what Blake said into one of the three operations (or the full backup).
- Run the right skill(s) in the order that cannot get stuck.
- Report back in plain language — never make Blake read git jargon.
Don't reimplement the git operations here — invoke the leaf skills with the Skill tool and follow their workflows; they own the actual commands. Decide which run and in what order. (Exception: the read-only status check below runs git directly, since it only looks and changes nothing.)
The three operations
| Skill | Plain meaning | Run it when Blake wants to… |
|---|---|---|
blake-os:git-commit |
Save his work into the project's history | save, lock in, record what he did |
blake-os:git-sync |
Pull down the newest version from GitHub | get the latest, see others' changes, refresh |
blake-os:git-push |
Send his saved work up to GitHub | upload, publish, put it online, make it live |
Read what he meant (intent map)
Match Blake's words to an intent. When more than one could fit, prefer the fuller action — a non-dev who says "save it" usually means "make sure it's safe," which is the full backup, not just a local commit.
| He says something like… | Intent | What to run |
|---|---|---|
| "back it up", "save everything", "I'm done", "make sure this is safe", "done for the day", "save and upload" | Full backup | the full chain below |
| "save my work", "save this", "record this", "lock it in" (and he clearly means local only) | Save | git-commit |
| "get the latest", "update", "what changed?", "did anything change online?", "refresh" | Get latest | git-sync |
| "upload", "send it", "put it online", "publish", "make it live", "push it up" | Upload | commit first if there are unsaved edits, then git-push |
| "is it saved?", "did it work?", "is it backed up?", "what's the status?" | Check | status check (below), then offer the fitting action |
| Anything vague or unclear | Full backup | the full chain below — it's always safe |
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.
- 2d ago First seen · 121 lines · 109 tokens per session scan A addd948a6b94
git-ops is a skill published in the GitHub repository basher83/lunar-claude (22 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 1,642 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
checkpoint-management
Git-backed state management for safe rollback. Create and restore checkpoints with tagged commits and metadata tracking.
push-all
Use when the user explicitly asks to stage all current changes, create a commit, and push to the remote after safety checks.
night-watch
Autonomous maintenance (dep updates, dead code, small refactors) in isolated branch, off-hours. Triggers: night watch, autonomous maintenance, dep updates.
what-did-i-get-done
Summarize authored commits over a user-specified time period into a concise update.
tools
Utility commands — commit, compile, validate-bib, journal, context-status, deploy, learn. Replaces individual utility skills.
lakefs-versioning
Use when lakeFS data versioning — Git-like branching for data lakes, atomic commits, time travel, CI/CD. Use when working with lakefs versioning.