lucide-mcp: Instructions file for Codex

AGENTS.md

lucide-mcp AGENTS.md is an instructions file for Codex, OpenCode from ViGi-P/lucide-mcp. It costs 481 tokens per session, scanned A, original, MIT.

Repository instructions for developing the lucide-mcp project, including its TypeScript layout, build commands, tests, coding style, and naming rules. Lucide is an icon library.

In plain words
What is it for?
Use them when building, testing, inspecting, or extending the lucide-mcp codebase.
Why use it?
They give contributors consistent rules for changing the project and checking that it still works.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is ViGi-P/lucide-mcp's own configuration. It tells Codex and OpenCode how to work on lucide-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lucide-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ViGi-P/lucide-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ViGi-P/lucide-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ViGi-P/lucide-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for lucide-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vigi-p/lucide-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/vigi-p/lucide-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/vigi-p/lucide-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/vigi-p/lucide-mcp/agents-md/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.

agentmods 80×15 button for lucide-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vigi-p/lucide-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/vigi-p/lucide-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 481 This file is loaded in full into every session.
When invoked 481 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00481 $0.00481
Opus 5 $0.00241 $0.00241
Sonnet 5 $0.00096 $0.00096
Haiku 4.5 $0.00048 $0.00048

Measured 9d ago against content hash dc4f2a3eefc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

lucide-mcp 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 9d 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 · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

  • src/ contains the TypeScript source.
  • src/server.ts wires the MCP server and tool registration.
  • src/cli.ts is the command-line entry point.
  • src/utils/ holds small helpers such as matching, tokenizing, and dictionary loading.
  • dist/ is the compiled output produced by TypeScript and is published in the package.
  • scripts/ contains maintenance scripts, including license generation.

Build, Test, and Development Commands

  • pnpm install installs dependencies.
  • pnpm build compiles src/ into dist/ with tsc -p tsconfig.json.
  • pnpm test currently runs the build and then launches the MCP inspector against dist/cli.js.
  • node dist/cli.js --help checks the CLI locally.
  • pnpm dlx @modelcontextprotocol/inspector node ./dist/cli.js inspects MCP tool behavior.
  • pnpm licenses:update regenerates THIRD_PARTY_LICENSES.md after dependency changes.

Coding Style & Naming Conventions

  • Use TypeScript with strict mode enabled.
  • Follow the existing style: 2-space indentation, double quotes, semicolons, and small focused functions.
  • Prefer descriptive file names that match exported responsibility, such as token-score.ts or load-dictionary.ts.
  • Keep changes minimal and avoid unrelated refactors.

Testing Guidelines

  • There is no separate test framework yet.
  • Treat pnpm build as the primary verification step.
  • If you add tests later, keep them close to the code they cover and document the command in package.json.

Commit & Pull Request Guidelines

  • This checkout does not expose git history, so no commit-message convention is enforced here.
  • Use concise, imperative commit subjects, for example: Add token filtering for icon search.
  • PRs should describe the behavior change, note any CLI or MCP contract impact, and mention if THIRD_PARTY_LICENSES.md was updated.

Configuration Notes

  • The dictionary cache is written under ~/.lucide-mcp/, not inside the repository.
  • Avoid committing generated files unless they are part of dist/ or another intentional release artifact.

Read the full file on GitHub · 44 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.

  1. 9d ago First seen · 44 lines · 481 tokens per session scan A dc4f2a3eefc4

Subscribe to this mod's changes

lucide-mcp AGENTS.md is an instructions file published in the GitHub repository ViGi-P/lucide-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 481 tokens to every session, about $0.0024 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.