What is uml-mcp AGENTS.md?

Workspace instructions for an MCP server that creates UML diagrams, which are visual maps of software structure and relationships. They record maintainer preferences, project facts, dependency practices, and diagram-skill locations.

Use them when maintaining the uml-mcp repository, its Python dependencies, GitHub Actions workflows, README, or UML diagram skills.

They help coding agents follow the repository's established documentation, dependency, CI, and diagram conventions.

How antoinebou12/uml-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to antoinebou12/uml-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/antoinebou12/uml-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/antoinebou12/uml-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/antoinebou12/uml-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/antoinebou12/uml-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/antoinebou12/uml-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/antoinebou12/uml-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/antoinebou12/uml-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/antoinebou12/uml-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 772 This file is loaded in full into every session.

When invoked 772 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.

Model	Per session	Once invoked
Fable 5.1	$0.00772	$0.00772
Opus 5.5	$0.00309	$0.00309
Sonnet 5.5	$0.00154	$0.00154
Haiku 4.5	$0.00077	$0.00077

Measured 13d ago against content hash a88656ca1614, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

uml-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 13d 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 · 20 lines

How it starts

The opening of the file, as written. The whole thing — 20 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learned User Preferences

In documentation and attributions, spell the maintainer name as Antoine Boucher; do not abbreviate it to "Antoine Bou".
Pin astral-sh/setup-uv in GitHub Actions to a full release tag (for example v8.1.0) or an explicit commit SHA; do not use a bare @v8 ref, because that action is not published as a floating major tag and Actions fails to resolve it.
For the root README.md, prefer compact markdown tables for reference-style blocks (for example environment variables with defaults, deployment URLs, MCP tools and uml:// resources) when improving scanability; keep deeper topics such as the diagram fallback pipeline in docs/ rather than duplicating them in the README unless asked.

Learned Workspace Facts

Python dependencies and the lockfile are driven by uv (pyproject.toml, uv.lock); after constraint changes, expect uv lock / uv sync and CI parity with uv lock --check where applicable; when the checked-in requirements.txt / requirements-dev.txt pins are maintained, regenerate them with uv export so they match the lockfile.
Diagram skills: MCP skills/list serves one workflow skill (skill://uml-mcp-diagrams/SKILL.md). Canonical copy in .skill/skills/uml-mcp-diagrams/SKILL.md; Claude Code plugin copy in plugins/uml-mcp/skills/uml-diagrams/SKILL.md; GitHub Copilot mirror in .github/skills/uml-mcp-diagrams/SKILL.md (byte-identical to the canonical copy, enforced by tests) used by the custom agent .github/agents/uml-mcp.agent.md. Each catalog diagram_type has an agent-only skill at .skill/skills/<diagram_type>/SKILL.md (agent-skills index; not on MCP skills/list). Cursor uses .cursor/mcp.json (hosted MCP) plus the .skill skill path—see docs/integrations/cursor.md.
Multi-version Python work in this repo has treated 3.12 as the primary baseline while also exercising 3.15 in CI matrices when supported; widening requires-python and regenerating the lock goes with that pattern.
Agent persona and principles live in SOUL.md; optional enterprise SSO (MCP_AUTH_MODE) lives in mcp_core/auth/ and docs/enterprise/. Never enable auth on Vercel; never forward client tokens downstream.

Read the full file on GitHub · 20 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.

13d ago Changed · +60 tokens per session a88656ca1614
14d ago Changed b4132cbf3bef
1mo ago Changed · +8 lines · +338 tokens per session 320e56f0f86a
2mo ago First seen · 12 lines · 374 tokens per session scan A 487dfee67ce3

Subscribe to this mod's changes

uml-mcp AGENTS.md is an instructions file published in the GitHub repository antoinebou12/uml-mcp (109 stars, last pushed yesterday), licensed MIT. It adds 772 tokens to every session, about $0.0031 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 2026-08-30.

mcp uml

uml-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
uml-mcp AGENTS.mdantoinebou12/uml-mcp	Instructions file	109	yesterday	MIT	A	772	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

uml-mcp: Instructions file for Codex