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/pivoshenko/pivoshenko.ai/git-commitnpx skills add pivoshenko/pivoshenko.ai --skill git-commitgit clone --depth 1 https://github.com/pivoshenko/pivoshenko.aiWhat 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 | $0.00090 | $0.01893 |
| Opus 5 | $0.00045 | $0.00946 |
| Sonnet 5 | $0.00018 | $0.00379 |
| Haiku 4.5 | $0.00009 | $0.00189 |
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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit
Conventional commit. No confirm. No dry-run.
Flow
- Parallel:
git status+git diff --staged. - Nothing staged -> stage relevant. Paths >
-A. Never.env/ creds / secrets. - Parallel:
git diff --staged(if just staged) +git log --oneline -5. - Read diff -> one commit or many (see Atomic) -> write msg.
- Commit now. Many groups + already mass-staged ->
git restore --staged .to unstage (modern idiom;git reset HEADalso fine), then stage+commit per group. Loop til clean. - Print hash + one-liner per commit.
Atomic
Mixed concerns -> split. No mega-commit.
Group by:
- type —
feat/fix/docs/refactor/testnever share - scope — diff modules/pkgs = diff commits
- logical unit — one thing per commit. Each builds + tests alone.
Split signals:
-
1 unrelated area
- behavior + format/rename mixed (format separate)
- summary needs "and" / "also" / "+"
- unsure -> ask user how to group
Msg format
<header>
<body>
<footer>
header required. body only when the header leaves a real "why" unanswered. footer optional.
Default = header only. Most commits ship with no body.
Header
<type>(<scope>): <short summary>
- type:
build|chore|ci|docs|feat|fix|perf|refactor|test - scope: optional. Affected area/module/pkg. Lowercase, kebab/short noun. One scope only — pick the dominant one, else omit.
- summary: imperative present ("add" not "added"/"adds"), lowercase, no trailing
. - whole header ≤ 72 chars. Tighter is better; aim ≤ 50 for the summary itself.
- no ticket IDs in header (go in footer). No emoji. No
[WIP].
Type pick
Pick the most specific. Behavior change > non-behavior. User-visible > internal.
SemVer bump column is the canonical mapping used by cliff.toml across all repositories. feat!: / BREAKING CHANGE: footer always → MAJOR regardless of type.
| Type | SemVer | Use when | Examples |
|---|---|---|---|
| feat | MINOR | New user-visible capability or API | new endpoint, new CLI flag, new component, new public function |
| fix | PATCH | Restoring intended behavior after a defect | crash on null input, wrong calc, regression repair |
| perf | PATCH | Same behavior, measurably faster / lighter | cache hot path, drop O(n²) loop, lazy-load |
| refactor | PATCH | Code shape changes; behavior identical | rename, extract, inline, move file, dedupe — no API or output change |
| test | none | Test files only | add coverage, fix flake, rename test |
| docs | none | Docs / comments / README / changelog only |
prose edits, JSDoc, ADRs, doc-only typos |
| build | none | Build system, deps, lockfiles, packaging | package.json deps, uv.lock, Dockerfile, bundler config |
| ci | none | CI/CD pipeline config | GH Actions workflow, release pipeline, branch protection scripts |
| chore | none | Repository maintenance with no code/build/CI/docs effect | .gitignore, editor config, tooling configs not tied to build |
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 · 179 lines · 90 tokens per session scan A 917b5222689a
git-commit is a skill published in the GitHub repository pivoshenko/pivoshenko.ai (4 stars, last pushed 3d ago), licensed MIT. It adds 90 tokens to every session and 1,893 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 2026-08-31.
Other skills, from other repositories
80-livekit-agents-majiayu000-claude-skill-registr
Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter.
80-livekit-agents-panaversity-agentfactory-1f8ecf89
Create your LiveKit Agents skill from official documentation, then learn to improve it throughout the chapter.
workers-best-practices
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from…
agent-architecture-planner
Use when designing an autonomous agent, planning agent architecture, building a scheduled automation, or creating a Claude Code agent workflow. Triggers: 'design an agent', 'build an automation', 'agent architecture', 'automate this workflow', 'create a scheduled agent', 'shell script agent'.
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.