Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/luismiglezmohino/ai-dev-agents/git)<a href="https://agentmods.dev/skills/luismiglezmohino/ai-dev-agents/git"><img src="https://agentmods.dev/badge/skills/luismiglezmohino/ai-dev-agents/git.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 | $0.00013 | $0.02155 |
| Opus 5 | $0.00006 | $0.01077 |
| Sonnet 5 | $0.00003 | $0.00431 |
| Haiku 4.5 | $0.00001 | $0.00215 |
Grade A, and why
git 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 6d 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 — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Git
REVIEW: This skill was generated with generic best practices. Adapt it to your project's conventions before using in production. Last review: 2026-02-24
Tech Stack
- Git >= 2.40
- Husky >= 9.0 (git hooks)
- GitHub Flow (simplified trunk-based)
- Conventional Commits 1.0.0
Project Patterns
Branch Naming
Format: <type>/<description-kebab-case>
feature/add-user-auth
fix/login-redirect-loop
docs/update-api-readme
refactor/extract-payment-service
chore/upgrade-dependencies
hotfix/critical-null-pointer
Rules:
- Always in English, kebab-case
- Short but descriptive (3-5 words max)
- Base branch:
main(neverdevelopin GitHub Flow) - Delete branch after merge
Conventional Commits
Format: <type>(<scope>): <description>
feat(auth): add JWT token refresh endpoint
fix(auth): correct token refresh on expired sessions
docs(api): update OpenAPI spec for /users endpoint
test(auth): add integration tests for login flow
refactor(domain): extract ValueObject base class
perf(search): add index for user full-text search
chore(deps): upgrade symfony to 7.2
Allowed types:
| Type | When to use | Example |
|---|---|---|
feat |
New feature | feat(dashboard): add drag-and-drop widgets |
fix |
Bug fix | fix(tts): handle empty text in speech synthesis |
docs |
Documentation only | docs(readme): add setup instructions |
test |
Add or fix tests | test(api): add e2e tests for auth flow |
refactor |
No behavior change | refactor(users): extract repository interface |
perf |
Performance improvement | perf(api): cache user profile responses |
chore |
Maintenance, deps, CI | chore(docker): update PHP base image |
ci |
CI/CD changes | ci(github): add deploy workflow |
Message rules:
- Description in imperative, lowercase, no trailing period
- Scope optional but recommended (affected module or layer)
- First line < 72 characters
- Optional body: separated by blank line, explains the "why"
- Footer:
BREAKING CHANGE:if it breaks compatibility,Closes #123for issues
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.
- 6d ago First seen · 301 lines · 13 tokens per session scan A 38d5e2bffbce
git is a skill published in the GitHub repository luismiglezmohino/ai-dev-agents (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 2,155 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 2026-08-31.
Other skills, from other repositories
spec-checkpoint
Create a comprehensive checkpoint commit with detailed analysis of all changes. Use this skill when the user says "checkpoint", "commit everything", "save my progress", "create a commit", or wants to stage and commit all current changes with a well-crafted message. Also use when the user says "/spec-checkpoint" (or…
git-commit
Run the simplest Git commit flow. Prefer $git commit; $git-commit remains a compatibility command.
git
Route specdrive Git actions by argument. Use when the user invokes $git, $git commit, or $git pr.
git-guardian
Pre-commit safety checks for AI-assisted development. Detects secrets, large files, merge conflict markers, sensitive files, and common AI-coding mistakes before they hit your repo.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
managing-git
Manages Git workflows including branching, commits, and pull requests. Use when working with Git, creating commits, opening PRs, managing branches, resolving conflicts, or when asked about version control best practices.