What is trellis-mcp CLAUDE.md?

A set of Claude Code instructions for Trellis MCP, a Python server that tracks projects, larger work items, features, and tasks in Markdown files. It defines a research, planning, implementation, and testing workflow.

Use it when changing the Trellis MCP server, updating its file-backed planning data, running checks, or completing tasks through its workflow.

It tells a coding agent how this project is organised and when work must stop until quality checks pass.

How langadventurellc/trellis-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to langadventurellc/trellis-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/langadventurellc/trellis-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/langadventurellc/trellis-mcp

Made for: Claude Code.

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/langadventurellc/trellis-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/langadventurellc/trellis-mcp/claude-md)

Your own site

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

Per session 1,407 This file is loaded in full into every session.

When invoked 1,407 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	$0.01407	$0.01407
Opus 5	$0.00704	$0.00704
Sonnet 5	$0.00281	$0.00281
Haiku 4.5	$0.00141	$0.00141

Measured 8d ago against content hash 16bb803552ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

trellis-mcp CLAUDE.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 8d 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.

CLAUDE.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md – System Prompt for Trellis MCP Coding Agents

Server purpose: File‑backed MCP server implementing the “Trellis MCP v 1.0” specification (Projects → Epics → Features → Tasks).

🗺️ Project Overview

Trellis MCP is a Python 3.12 JSON‑RPC server built on FastMCP.
It stores all state as Markdown files with YAML front‑matter in a nested tree:

planning/projects/P‑…/epics/E‑…/features/F‑…/tasks-open/T‑….md

🚦 Quality Gate — “GREEN or STOP 🚫”

Mandatory - Run all checks before committing:

uv run poe quality                   # isort, black, flake8, pyright
uv run pre-commit run --all-files    # Alternative: run checks on git-staged files only

Any ❌ = block. Fix → re‑run → commit. Repeat until all checks pass.

🔄 Workflow (Research → Plan → Implement)

Research – Browse code & spec. Ask questions if requirements are fuzzy.
Plan – Draft a concise step list; confirm interfaces, files, tests.
Implement – Code & tests → run quality gate → update task ### Log with a one‑paragraph summary + filesChanged[] → call completeTask → STOP.

🔧 Common Commands

Goal	Command
Install dependencies	`uv sync`
Install for development	`uv pip install -e .`
All quality checks	`uv run poe quality`
Run unit tests	`uv run pytest -q`

CLI Commands

See docs/api/cli-commands.md for a full list of CLI commands.

📑 Coding Standards

flake8/black decide style—no bikeshedding.
Functions ≤ 40 LOC; classes ≤ 200 LOC; refactor otherwise.
Prefer composition over inheritance.
One logical concept per file.
See Clean‑Code Charter below.

Type Checking

Prefer built-in types (list, dict, etc.) over typing.List, typing.Dict unless necessary
Use union operator for optional types (e.g., str | None instead of Optional[str])

Clean‑Code Charter

Read the full file on GitHub · 127 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.

8d ago First seen · 127 lines · 1,407 tokens per session scan A 16bb803552ad

Subscribe to this mod's changes

trellis-mcp CLAUDE.md is an instructions file published in the GitHub repository langadventurellc/trellis-mcp (0 stars, last pushed 1y ago), licensed MIT. It adds 1,407 tokens to every session, about $0.0070 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.

Planning Project management

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

trellis-mcp: Instructions file for Claude Code