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/jgt87/local-llm-mcpWrote 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/jgt87/local-llm-mcp/local_commit)<a href="https://agentmods.dev/commands/jgt87/local-llm-mcp/local_commit"><img src="https://agentmods.dev/badge/commands/jgt87/local-llm-mcp/local_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/jgt87/local-llm-mcp/local_commit"><img src="https://agentmods.dev/badge/commands/jgt87/local-llm-mcp/local_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 | $0.00017 | $0.00448 |
| Opus 5.5 | $0.00007 | $0.00179 |
| Sonnet 5.5 | $0.00003 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
local_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 5d 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.
What it actually says
Context from the user (may be empty): $ARGUMENTS
Draft a commit message with local_ask.
- Run
git diff --staged. If nothing is staged, rungit diffand say the message covers unstaged changes. If there are no changes at all, stop and say so. - Run
git log --oneline -10to see the repository's subject style. - Send the diff to local_ask. Leave out lockfiles, binaries and generated output, and trim very large hunks to their headers. System prompt: write a commit message in the style of the example subjects (include them), an imperative subject under 72 characters, then a blank line and a short body explaining why. Output only the message. Use maxTokens around 150.
- Check the draft against the diff: every claim must be true of the change, and nothing important may be missing. Correct it.
- Show the final message. Do not commit unless the user asked you to.
Ground rules:
- Use the local-llm tools for the generation step; do the reading, trimming and checking yourself. The local model has no file access, no repo context and no memory between calls, so every call must carry all the text it needs.
- Keep maxTokens tight: locally it runs at roughly 16 tokens per second.
- Stay on the default provider unless the user asked for OpenRouter. Never send secrets, keys or private data to provider="openrouter".
- If a call fails because Ollama is unreachable, say so and stop; do not silently do the work yourself instead.
- Treat the reply as a draft. Check it against the source before presenting it, fix what is wrong, and say briefly what you changed.
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.
- 5d ago First seen · 25 lines · 17 tokens per session scan A 6625fd2f7953
local_commit is a command published in the GitHub repository jgt87/local-llm-mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 17 tokens to every session and 448 once invoked, about $0.0001 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 2026-10-27.
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.