workflowyMCP CLAUDE.md

Repository instructions for WorkflowyMCP, a project governed by a constitution and supporting principle documents that define how work must be done.

In plain words
What is it for?
Use them when changing WorkflowyMCP code, architecture, naming, error handling, helper functions, or other areas covered by its principle documents.
Why use it?
They ensure every task follows the project’s required design, development, and completion rules before and after changes.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/dromologue/workflowymcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/dromologue/workflowyMCP
Per session 29,849 This file is loaded in full into every session.
When invoked 29,849 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 $0.29849 $0.29849
Opus 5 $0.14925 $0.14925
Sonnet 5 $0.05970 $0.05970
Haiku 4.5 $0.02985 $0.02985

Measured 2d ago against content hash 7b7e87c730a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflowyMCP 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 2d 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 · 363 lines

How it starts

The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Read This First — Project Constitution + Principle Docs

This project is governed by a constitution and four detail-principle documents. Every task in this repository — from a one-line fix to a multi-file refactor — must be bracketed by reading the relevant docs at the start and verifying against them at the end. The reading is not optional; it is the project's enforcement mechanism for consistency across contributors (human or AI).

The five canonical documents

Document When to consult
specs/constitution.md Always, before starting any non-trivial task. Eight Core Principles, the Definition of Done checklist, and the Conflict-Resolution Hierarchy. The law.
specs/principles-architecture.md When the task touches module boundaries, the lift catalogue (workflows.rs / aggregation.rs / audit.rs), the helper inventory, or any pin-tested invariant. Read the relevant section before editing.
specs/principles-development.md When the task involves naming, error handling shape, function-size judgements, helper extraction, or code style. The Rust idioms section is the canonical pattern catalogue.
specs/principles-mcp.md When the task adds or modifies a tool, changes wire-surface behaviour, touches pagination/caps, modifies error envelopes, or affects the dry-run / cancel / timeout machinery.
specs/principles-security.md When the task touches authentication, secrets, logging, error messages exposed to users, audit-trail emission, or any external input validation.

Task lifecycle — every task, every time

The following ritual is mandatory for every task that ships a commit. Skipping any step is a defect — call it out in the response rather than silently omitting it.

Read the full file on GitHub · 363 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. 2d ago First seen · 363 lines · 29,849 tokens per session scan A 7b7e87c730a6

Subscribe to this mod's changes

workflowyMCP CLAUDE.md is an instructions file published in the GitHub repository dromologue/workflowyMCP (10 stars, last pushed 12d ago), licensed MIT. It adds 29,849 tokens to every session, about $0.1492 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.