What is llmc AGENTS.md?

A repository-specific instruction file for llmc, a Node.js and TypeScript command-line tool that creates Conventional Commits messages from Git changes.

Use it when working on llmc's CLI, commit-message generation, provider loading, configuration, user interface, or Git-hook integration.

It gives coding agents the project's overview, architecture, supported AI providers, and development conventions before they change the code.

llmc AGENTS.md — Instructions file by marclove

Install

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.

agentmods

npx agentmods add instructions/marclove/llmc/agents-md

Clone the repo

git clone --depth 1 https://github.com/marclove/llmc

Made for: Codex, OpenCode.

Per session 2,152 This file is loaded in full into every session.

When invoked 2,152 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02152	$0.02152
Opus 5	$0.01076	$0.01076
Sonnet 5	$0.00430	$0.00430
Haiku 4.5	$0.00215	$0.00215

Measured 2d ago against content hash d0ec790da620, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

llmc AGENTS.md 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 2d 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.

AGENTS.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to agentic coding agents like Claude Code, Gemini CLI, and Codex CLI when working with code in this repository.

Project Overview

llmc is an AI-powered commit message generator that creates Conventional Commits-compliant messages from git diffs. It's a Node.js/TypeScript CLI tool that supports multiple AI providers (Anthropic, OpenAI, Google, etc.) and can be integrated with git hooks. The tool offers two modes: automatic commit mode (default) and message-only mode for git hook integration.

Architecture

Core Components

index.ts: Main CLI entry point and orchestrator with command-line argument parsing for message-only mode
app.tsx: React-based application logic with git integration, CLI rendering, and dual-mode support
message.ts: Core message generation logic with AI provider integration- providers.ts: Dynamic provider loading system supporting 13+ AI services
config.ts: Configuration management with TOML support and type-safe defaults
cli.tsx: React component for CLI interface with ink for progress indicators and status messages

Key Design Patterns

Dynamic Provider Loading: Providers are loaded on-demand to reduce bundle size
Configuration Hierarchy: TOML config file → environment variables → sensible defaults
Structured Generation: Uses generateObject with Zod schema for reliable output
Template Interpolation: Custom prompts support ${diff} placeholders
React-based CLI: Uses ink for rich terminal UI with spinners and real-time status updates
Separation of Concerns: index.ts remains simple .ts for compatibility, React/JSX logic in .tsx files
Snake/Camel Case Conversion: Automatic conversion between TOML snake_case and TypeScript camelCase
Comprehensive Testing: Full test coverage with unit, integration, and UI testing strategies

Read the full file on GitHub · 203 lines

Changes

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.

2d ago First seen · 203 lines · 2,152 tokens per session scan A d0ec790da620

Subscribe to this mod's changes

llmc AGENTS.md is an instructions file published in the GitHub repository marclove/llmc (10 stars, last pushed 10mo ago), licensed BSD-3-Clause. It adds 2,152 tokens to every session, about $0.0108 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.

claude claude-code cline codex-cli conventional-commit conventional-commits

llmc AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Project Overview

Architecture

Core Components

Key Design Patterns

What this file has done since we first saw it

Other instructions, from other repositories

MDDesign AGENTS.md

MDDesign CLAUDE.md

MDDesign GEMINI.md

known AGENTS.md

known CLAUDE.md

known GEMINI.md