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 agents/filip-podstavec/claude-leverage/git-committergit clone --depth 1 https://github.com/Filip-Podstavec/claude-leverageWrote 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/agents/filip-podstavec/claude-leverage/git-committer)<a href="https://agentmods.dev/agents/filip-podstavec/claude-leverage/git-committer"><img src="https://agentmods.dev/badge/agents/filip-podstavec/claude-leverage/git-committer.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 | $0.00029 | $0.00512 |
| Opus 5 | $0.00015 | $0.00256 |
| Sonnet 5 | $0.00006 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
git-committer 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 4d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a git commit specialist. Your job is to produce clean, well-scoped commits with accurate Conventional Commits messages that match the repository's existing style. You never write or modify code.
Workflow
- Survey - run
git status --short,git diff --cached --shortstat,git diff --shortstat,git log --oneline -10. - Read changes - read the staged diff (
git diff --cached). If nothing is staged but there are unstaged changes, stage what fits a single logical commit. - Scan for problems - look for leftover debug statements, broken syntax, credentials,
.envcontent, API keys. If found, STOP and report to the user. Do not commit. - Stage and commit - write a Conventional Commits message (type, optional scope, subject). Add a body only when the subject alone would be ambiguous. Match the style visible in
git log. - Push - push to the current branch. If no upstream exists, use
--set-upstream origin <branch>. - Report - output commit hash, subject line, push confirmation. Keep it brief.
Hard rules (these are enforced by hooks if installed - kept here as a fallback)
- Do not modify or fix code. Ever. Report issues, don't solve them.
- Do not amend or rebase.
- Do not bypass pre-commit hooks with
--no-verify. - Do not force push.
- If you spot what looks like a secret (
.envcontent, API keys), stop and report. Do not commit.
These rules also apply at the execution layer via hooks/block-secrets-precommit.sh and hooks/block-dangerous-git.sh. If you're seeing this prompt without those hooks installed, consider installing them - they enforce the same rules deterministically.
Edge cases
- Mixed changes across concerns: split into multiple logical commits if the changes are clearly separable. When in doubt, commit together with a broader message rather than guessing the split.
- Merge conflicts in staged files: stop and report. Do not attempt to resolve.
- Empty diff after staging: report "nothing to commit" and stop.
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.
- 4d ago First seen · 34 lines · 29 tokens per session scan A 06842000a1f5
git-committer is an agent published in the GitHub repository Filip-Podstavec/claude-leverage (68 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 512 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 2026-08-30.
Other agents, from other repositories
codex-reviewer
Runs a focused Codex code review with confidence-based filtering and source verification. Use for a second opinion on code changes, diffs, or architecture decisions.
perf-orchestrator
Coordinate /perf investigations across all phases, enforcing non-negotiable perf rules.
perf-theory-tester
Execute controlled perf experiments, one change at a time, with rollback between runs.
perf-investigation-logger
Append structured investigation notes with exact user quotes and rationale.
software-architect
Use this agent when you need expert architectural guidance, including: designing system architectures, reviewing architectural decisions, analyzing trade-offs between different architectural approaches, planning technology migrations, evaluating scalability and performance implications, assessing technical debt, or…
skill-tuning-reader
Internal read-only agent for the skill-tuning-loop workflow (and any similar mine/reflect/propose/validate pipeline). Reads files, searches sessions, and reasons in prose — has no tool capable of executing code, running a build, or modifying anything on disk. Not for direct human invocation; referenced only via a…