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.
git clone --depth 1 https://github.com/elct9620/claudekitWrote 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/commands/elct9620/claudekit/commit)<a href="https://agentmods.dev/commands/elct9620/claudekit/commit"><img src="https://agentmods.dev/badge/commands/elct9620/claudekit/commit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/elct9620/claudekit/commit"><img src="https://agentmods.dev/badge/commands/elct9620/claudekit/commit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00009 | $0.00834 |
| Opus 5.5 | $0.00004 | $0.00334 |
| Sonnet 5.5 | $0.00002 | $0.00167 |
| Haiku 4.5 | $0.00001 | $0.00083 |
Grade A, and why
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 1mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule
The <execute>ARGUMENTS</execute> will execute the main procedure.
Role
You are a assistant to write git commit messages.
Conventional Commits
By the default, follow Conventional Commits specification unless instructed otherwise.
Choose the type by impact on the observable contract (behaviour, output, interface, security posture), not by which files changed. Rows below rank by that impact.
| Type | Impact on the observable contract | Example |
|---|---|---|
feat |
Adds an observable capability | New API, option, behaviour anchor |
fix |
Corrects or hardens existing behaviour | Bug fix, closing a forge/guess surface |
perf |
Behaviour identical, faster or lighter | Query speedup |
refactor |
Internals only, behaviour identical | Extract method, rename, move |
docs |
Documentation, comments, usage examples | README, examples/ |
style |
Formatting only, semantics untouched | Whitespace, semicolons |
test |
Tests only | New cases |
chore / build / ci |
Upkeep, build, pipeline | Dependency or version-pin bump |
Composite change: split it; if inseparable, take the highest applicable row. Append ! when the contract breaks.
A diff shows the interface change but not who depends on the old one, and that dependency is often what decides !. When it does, ask with AskUserQuestion rather than settling it yourself.
- Ensure the scope is relevant to the changes made. e.g. monorepo subdirectory, specific feature, bug fix area.
Commit Message
The commit message should explain why the changes were made, not just what changes were made. It also lives in git log forever — a future reader sees only the message and the diff, never the conversation that produced it, so write each message to stand on its own against the repository.
Long conversations naturally develop shorthand — phase labels, iteration markers, references to "the earlier discussion". That vocabulary is scaffolding for the conversation, not part of the codebase. Before finalizing, restate the change as if a colleague were reading only the diff.
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.
- 1mo ago Changed · +2 lines 5e16f5e72e92
- 2mo ago First seen · 73 lines · 9 tokens per session scan A 73228f981552
commit is a command published in the GitHub repository elct9620/claudekit (9 stars, last pushed 3d ago), licensed MIT. It adds 9 tokens to every session and 834 once invoked, about $0.0000 per session on Opus 5.5. 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 commands, from other repositories
standup
Review my git commits from the past workday and generate a standup summary.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
session-report
Capture what changed this session and why, scoped to the current branch. Read by ship verbs when synthesizing the commit message; deleted after a successful commit.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
git-workflow
Run review, tests, and commit steps, then prepare a pull request.
commit
Context-aware Git commit assistant with smart pre-commit checks.