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/fredrikaverpil/dotfiles/git-commitnpx skills add fredrikaverpil/dotfiles --skill git-commitgit clone --depth 1 https://github.com/fredrikaverpil/dotfilesWhat 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 | $0.00043 | $0.00730 |
| Opus 5 | $0.00022 | $0.00365 |
| Sonnet 5 | $0.00009 | $0.00146 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
git-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 yesterday.
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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit Messages
Write commit messages following the Conventional Commits specification.
Format
<type>(<scope>): <description>
[optional body]
[optional footer(s)]
Types
| Type | Purpose |
|---|---|
feat |
New feature |
fix |
Bug fix |
docs |
Documentation only |
style |
Code style (formatting, no logic change) |
refactor |
Code change that neither fixes a bug nor adds a feature |
perf |
Performance improvement |
test |
Adding or correcting tests |
build |
Build system or external dependencies |
ci |
CI configuration |
chore |
Maintenance tasks |
revert |
Reverts a previous commit |
Rules
- Use imperative mood in description ("add feature" not "added feature")
- Do not end description with a period
- Keep description under 72 characters
- Separate subject from body with a blank line
- Use the body to explain intent, nuances, gotchas, or background behind the change — not a paraphrase of the diff
- Always ask me for the Jira ticket number before committing. If there is one,
include it as the last line in the commit body (e.g.,
XY-123). If there isn't one, ask whether to create one.
Breaking Changes
Add ! after type/scope or include BREAKING CHANGE: in footer:
feat(api)!: remove deprecated endpoints
BREAKING CHANGE: The /v1/users endpoint has been removed.
Scope
Optional. Use to specify area of change (e.g., api, ui, auth, db).
Branch Naming
When creating a new branch, name it <type>/<jira-ticket> with the ticket
lowercased, using the same types as commit messages (e.g., feat/xy-123,
fix/xy-456). If there is no Jira ticket, fall back to
<type>/<kebab-description> (e.g., feat/add-user-auth).
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.
- yesterday First seen · 88 lines · 43 tokens per session scan A 8e9dfeb4c92d
git-commit is a skill published in the GitHub repository fredrikaverpil/dotfiles (256 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 730 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
userscripts
Use when writing Tampermonkey/Violentmonkey/Greasemonkey userscripts, modifying website behavior or appearance, or working with .user.js files.
subagent-driven-development
Use when executing implementation plans with independent tasks in the current Pi session using fresh subagents and review loops.
pr
Use when the user wants to create a new pull request, update an existing PR's body, open a draft PR, or preview a PR body locally before pushing.
writing-plans
Use when you have an approved design or requirements for a multi-step task, before touching code.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.