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/magic3007/dotfiles/smart-commitnpx skills add magic3007/dotfiles --skill smart-commitgit clone --depth 1 https://github.com/magic3007/dotfilesWrote 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/magic3007/dotfiles/smart-commit)<a href="https://agentmods.dev/skills/magic3007/dotfiles/smart-commit"><img src="https://agentmods.dev/badge/skills/magic3007/dotfiles/smart-commit.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 | $0.00019 | $0.02115 |
| Opus 5 | $0.00010 | $0.01058 |
| Sonnet 5 | $0.00004 | $0.00423 |
| Haiku 4.5 | $0.00002 | $0.00212 |
Grade A, and why
smart-commit 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Commit
Analyze all currently staged git changes, group them by logical concern, and create multiple well-structured commits following Conventional Commits v1.0.0.
Usage
Invoke with /smart-commit or when the task matches.
Arguments:
--dry-run: Only show the proposed commit plan without executing
Conventional Commits Specification
Every commit message MUST follow this format:
<type>[optional scope][optional !]: <description>
[optional body]
[optional footer(s)]
Types
| Type | When to Use |
|---|---|
feat |
A new feature (correlates with MINOR in SemVer) |
fix |
A bug fix (correlates with PATCH in SemVer) |
docs |
Documentation only changes |
style |
Formatting, missing semi-colons, etc. (not CSS) |
refactor |
Code change that neither fixes a bug nor adds a feature |
perf |
Performance improvement |
test |
Adding or correcting tests |
build |
Changes to build system or external dependencies |
ci |
Changes to CI configuration files and scripts |
chore |
Other changes that don't modify src or test files |
revert |
Reverts a previous commit |
The 50/72 Rule & Formatting Rules
Subject line (first line):
- Separate subject from body with a blank line
- Limit the entire subject line to ~50 characters (type + scope + description combined). Hard limit: 72 chars.
- Capitalize the description after
<type>(scope): - No period at the end of the subject line
- Use imperative mood
- All commit messages in English
Body:
- Wrap at 72 characters
- Explain what and why, not how
Scope & Breaking Changes:
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 · 295 lines · 19 tokens per session scan A 7d4dc3d80c96
smart-commit is a skill published in the GitHub repository magic3007/dotfiles (11 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 2,115 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 skills, from other repositories
ship
Generate a conventional commit message from staged or unstaged changes and create an atomic commit, then optionally push and watch CI until it passes or fails. Use when the user says "write a commit", "generate a commit message", "commit this", "git add .", or "ship this". Push and CI-watch are optional and skipped if…
commit
Commit the changes in the working tree. Only invoke when the user explicitly signals to commit ("commit", "/commit", etc.). Never invoke this skill on your own initiative — implementation approval is not a commit signal.
self-review
Self-review of code changes (branch diff, staged, or uncommitted). Use when: reviewing code before pushing, checking diff quality, self-reviewing a PR, creating a PR (always use --peer), reviewing uncommitted work. Triggers on: '/self-review', 'review my changes', 'review this branch', 'self-review', 'pre-push…
commit
Create conventional commits. Use when: committing staged changes. Triggers on: '/commit', 'conventional commit'.
orchestrate-agents
Orchestrate multiple agent CLIs (Claude, Codex, Antigravity) via tmux with a shared fleet store, dispatching one guardian subagent per pane. Survey-first: inspects and adopts existing tmux sessions, windows, and agent panes before creating anything new. Use when running a multi-agent session, dispatching parallel…
assess-quality
Foundational quality framework: the five questions (readable, easy to start, expands without bloat, consistent, intentional) every other dev skill is judged against, plus the dual-audience and workshop principles. Use when onboarding to a project, defining a quality bar, setting an assessment checklist, or arbitrating…