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.
git clone --depth 1 https://github.com/Amey-Thakur/AI-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/commands/amey-thakur/ai-skills/git-help)<a href="https://agentmods.dev/commands/amey-thakur/ai-skills/git-help"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/git-help.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 | $0.00023 | $0.00394 |
| Opus 5 | $0.00012 | $0.00197 |
| Sonnet 5 | $0.00005 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
git-help 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 4d 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
You were invoked as a slash command. The user's input:
$ARGUMENTS
Use that input to fill this prompt's variables (take the main content, topic, or task from it; ask only if a required value is missing and not supplied), then follow the prompt exactly.
Help me with git: {situation}
Current state: {state}
Provide:
- The command(s), in a code block, in the right order, for my actual state (committed vs not, pushed vs not: this changes the safe approach completely).
- A plain explanation of what each command does and why, so I understand it before running it and learn for next time.
- Safety flags: mark anything destructive or history-rewriting (
reset --hard,push --force,rebase,clean -fd,checkout --): what it throws away and whether it is recoverable. For risky operations, show the safer alternative (--force-with-leaseover--force, a backup branch before a rebase) and how to preview first. - If the change is already pushed and shared, warn about rewriting shared
history and prefer a safe forward fix (
revert) over a rewrite.
Rules: correctness and safety first (a wrong git command can lose work).
Prefer the recoverable approach; when I might lose commits, tell me how to find
them again (reflog). If my described state is ambiguous in a way that changes
the safe command, ask before giving a destructive one. Never suggest
push --force to a shared branch without a loud warning and the
--force-with-lease alternative.
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.
- 4d ago First seen · 40 lines · 23 tokens per session scan A 1f72d4ee1860
git-help is a command published in the GitHub repository Amey-Thakur/AI-SKILLS (7 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 394 once invoked, about $0.0001 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 commands, from other repositories
remove-deadcode
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits.
update-deps
Audit outdated dependencies, research breaking changes, update one at a time, verify each, commit separately.
commit
Create one conventional commit from an already-scoped change; never push.
release-prep
Review the local working tree, commit, push, open a PR, drive it merge-ready — do not merge.
get-unpublished-changes
Compare HEAD with the latest published npm versions and list all unpublished changes by release layer.
commit
Run when user calls /commit or asks to generate a commit message. Analyzes staged changes and writes a structured commit message.