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/anilcancakir/claude-code-plugins/commit-changesnpx skills add anilcancakir/claude-code-plugins --skill commit-changesgit clone --depth 1 https://github.com/anilcancakir/claude-code-pluginsWhat 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 | $0.00024 | $0.00441 |
| Opus 5 | $0.00012 | $0.00220 |
| Sonnet 5 | $0.00005 | $0.00088 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
commit-changes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Commit Task
Create a commit for staged/unstaged changes following project conventions.
Steps
- Check
git statusfor changes - Analyze
git log --oneline -10to detect commit style - Categorize changes (feat/fix/docs/refactor/test/chore)
- Generate commit message matching detected style
- Present to user for approval
- Execute commit
Commit Style Detection
Use the detection script for accurate results:
# Returns JSON with style and confidence
"${CLAUDE_PLUGIN_ROOT}/scripts/detect-commit-style.sh"
Output example:
{
"style": "conventional-scoped",
"confidence": 80,
"stats": { "total": 10, "conventional_scoped": 8, "gitmoji": 2 }
}
| Pattern | Style |
|---|---|
type(scope): message |
Conventional Commits (scoped) |
type: message |
Conventional (no scope) |
:emoji: message |
Gitmoji |
| Plain text | Simple |
Conventional Commits Types
| Type | Use For |
|---|---|
| feat | New features |
| fix | Bug fixes |
| docs | Documentation only |
| style | Formatting changes |
| refactor | Code restructuring |
| perf | Performance improvements |
| test | Adding/fixing tests |
| chore | Maintenance tasks |
Message Format
<type>(<scope>): <subject>
<body>
<footer>
Subject Rules:
- Imperative mood ("add" not "added")
- No period at end
- Max 50 characters
- Lowercase
Body (optional):
- Explain what and why
- Wrap at 72 characters
Footer (optional):
Closes #123BREAKING CHANGE: description
Output
Present message for approval before committing.
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 · 84 lines · 24 tokens per session scan A 6b19f6f33bb3
commit-changes is a skill published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 24 tokens to every session and 441 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
system-boot
Auto-activating session startup - reads memory, orients Claude, announces status. Triggers on session start or when user says "continue", "weiter", "resume".
project-brain
Triggers (all require explicit user request — do NOT activate just because a brain/ folder exists): (1) The user wants to set up project-level memory ("set up project brain", "scaffold project context", "init project brain", "建项目脑"). (2) The user is in a directory containing brain/ AND explicitly asks to resume /…
subagent-strategy
Delegates research and parallel work to sub-agents.
evolution-guide
Explains how Evolving Lite works when the user asks about the system, its features, or how to use it. Triggers on questions like "how does this work", "what is evolving lite", "what hooks are running", "explain the system".
spawn-agent
Spawn worker agents (Gemini CLI or Codex CLI) to keep main context clean. Use for implementation, codebase research, context gathering, or any scoped work that would pollute the orchestrator's context.
flutter-bloc-development
Build Flutter features using BLoC state management, clean architecture layers, and the project's design system. Apply when creating screens, widgets, or data integrations.