Borrowing it
Nothing to install: this file belongs to miguelcc06/front-design-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.
curl -O https://raw.githubusercontent.com/miguelcc06/front-design-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/miguelcc06/front-design-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/instructions/miguelcc06/front-design-mcp/agents-md)<a href="https://agentmods.dev/instructions/miguelcc06/front-design-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/miguelcc06/front-design-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.01010 | $0.01010 |
| Opus 5 | $0.00505 | $0.00505 |
| Sonnet 5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
Grade D, and why
front-design-mcp AGENTS.md scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get install -y postgresql postgresql-16-pgvector Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
`curl -LsSf https://astral.sh/uv/install.sh | sh` then `export PATH="$HOME/.local/bin:$PATH"`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -LsSf https://astral.sh/uv/install.sh | sh` then `export PATH="$HOME/.local/bin:$PATH"`. How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Notes for coding agents working in this repository. Human contributors should read CONTRIBUTING.md first; this file covers the non-obvious setup and the conventions that are easy to get wrong.
What this repo is
front-design-mcp is a FastMCP server (stdio) that gives agents frontend UI/UX
intelligence over an indexed catalog of components, patterns, and motion libraries.
It is a real Python package with two storage backends, not a documentation repo.
It also vendors Anthropic's mcp-builder agent skill under .agents/skills/mcp-builder/.
Do not edit that tree or skills-lock.json in routine changes — it is pinned
upstream content.
Environment
- Python 3.11 or 3.12. Dependencies are managed with uv and pinned in
uv.lock. - Canonical setup:
uv sync --all-extras --frozen. This installs thedev,postgres, andembeddingsextras. It deliberately does not install the heavy local embedding provider, which lives in a uv dependency group:uv sync --group local. uvis not always preinstalled on a fresh machine:curl -LsSf https://astral.sh/uv/install.sh | shthenexport PATH="$HOME/.local/bin:$PATH".
PostgreSQL for the optional backend
Only needed when working on the PostgreSQL/pgvector path. Either docker compose up -d
(see docker-compose.yml) or a local server with the pgvector extension:
sudo apt-get install -y postgresql postgresql-16-pgvector
sudo pg_ctlcluster 16 main start
sudo -u postgres psql -c "CREATE ROLE front_design LOGIN PASSWORD 'front_design' SUPERUSER;"
sudo -u postgres createdb -O front_design front_design_test
The PostgreSQL tests need FRONT_DESIGN_TEST_DATABASE_URL and create their own scratch
databases, so the role must be allowed to CREATE DATABASE. Without that variable the
whole PostgreSQL suite skips, and uv run pytest -q must stay green offline.
Gotchas that have already bitten people
- Never export
FRONT_DESIGN_*into a long-lived shell. Settings are read from the environment and from.env, so a stray export silently changes behaviour and test outcomes.tests/conftest.pystrips these variables for the duration of each test (keeping onlyFRONT_DESIGN_TEST_DATABASE_URL); pass configuration per command instead. - The vector dimension is fixed when the PostgreSQL schema is migrated. It comes from
FRONT_DESIGN_EMBEDDING_DIMENSIONS, or is derived from the provider and model. There is no default and there must never be one — seesrc/front_design_mcp/embeddings/dimensions.py. - Changing the embedding model invalidates stored vectors even at the same dimension. The search service refuses the vector branch on a mismatch rather than returning meaningless scores. Re-run ingest to re-embed.
fastembeddownloads models from HuggingFace on first use. Tests must never depend on that; use injected fakes.- Do not import a concrete store anywhere except
store/factory.py, and do not import thetoolspackage from retrieval code — that is why framework helpers live insrc/front_design_mcp/frameworks.pyrather than undertools/.
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.
- 6d ago First seen · 83 lines · 1,010 tokens per session scan D 8ddca3ee9120
front-design-mcp AGENTS.md is an instructions file published in the GitHub repository miguelcc06/front-design-mcp (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,010 tokens to every session, about $0.0051 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.