lucius-mcp AGENTS.md

lucius-mcp AGENTS.md is an instructions file for Codex, OpenCode from ivanostanin/lucius-mcp. It costs 374 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Lucius MCP, a Python software project that connects an AI agent to external tools through the Model Context Protocol. They define the required development process, environment, testing, and contribution rules.

In plain words
What is it for?
Use them before changing code, specifications, tests, telemetry, or project stories, and when setting up the Python environment or running tests and quality checks.
Why use it?
They prevent contributors from skipping project documentation, using the wrong Python setup, or making changes that violate privacy and scope requirements. They also standardize checks before sharing changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; built for openclaw.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/node/.openclaw/codespaces/.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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 lucius-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ivanostanin/lucius-mcp/agents-md.svg)](https://agentmods.dev/instructions/ivanostanin/lucius-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ivanostanin/lucius-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ivanostanin/lucius-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 374 This file is loaded in full into every session.
When invoked 374 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00374 $0.00374
Opus 5 $0.00187 $0.00187
Sonnet 5 $0.00075 $0.00075
Haiku 4.5 $0.00037 $0.00037

Measured 6d ago against content hash a5fcbd957ca2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

lucius-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 6d 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 · 50 lines

What it actually says

AGENTS.md

Project instructions for agents working in lucius-mcp.

Start Here

Before making any code, spec, or test changes:

  1. Read docs/development.md.
  2. Check current git state so you understand the active branch and any in-flight work.
  3. Prefer existing project docs and specs over guesswork.

Do not skip step 1.

Python Environment

  • Use uv, not bare python/pip, for project environment setup and commands.
  • Sync dependencies with:
uv sync --all-extras
  • Run project commands with uv run, for example:
uv run pytest tests/unit tests/integration
uv run ruff check .
uv run mypy src
  • If a task needs Python 3.13+, use uv to provision and run the correct interpreter instead of falling back to the system python3.

Change Discipline

  • Keep changes scoped to the requested task.
  • Do not use throwaway clones in /tmp for normal repo work; use this persistent checkout under /home/node/.openclaw/codespaces/.
  • When touching telemetry, preserve the privacy constraints documented in docs/development.md.
  • When updating stories or sprint artifacts, keep them consistent with the code and tests.

Pull Request Defaults

  • When creating a pull request, use a Conventional Commit title and complete the repository's existing pull-request template unless the user instructs otherwise.

Validation

  • Run the smallest relevant checks first.
  • If full validation is too heavy, run focused checks on touched areas and say what was not run.
  • Do not claim tests passed unless you actually ran them in this repo.
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. 6d ago First seen · 50 lines · 374 tokens per session scan A a5fcbd957ca2

Subscribe to this mod's changes

lucius-mcp AGENTS.md is an instructions file published in the GitHub repository ivanostanin/lucius-mcp (7 stars, last pushed 4d ago), licensed Apache-2.0. It adds 374 tokens to every session, about $0.0019 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.