What is proofhub-mcp CLAUDE.md?

A maintainer guide for ProofHub MCP, a Claude Code plugin that connects an AI coding assistant to ProofHub and includes a command-line tool. MCP is a way for an AI assistant to use external tools through a standard connection.

Use it when developing, testing, releasing, or packaging the proofhub-mcp plugin. It also explains the project layout and non-negotiable setup rules.

It records rules that protect the plugin’s packaging, credentials, release process, and communication format. This helps maintainers avoid broken installations, leaked keys, and invalid server output.

How yashmody/proofhub-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to yashmody/proofhub-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/yashmody/proofhub-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/yashmody/proofhub-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/yashmody/proofhub-mcp/claude-md.svg)](https://agentmods.dev/instructions/yashmody/proofhub-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/yashmody/proofhub-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/yashmody/proofhub-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 937 This file is loaded in full into every session.

When invoked 937 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	$0.00937	$0.00937
Opus 5	$0.00468	$0.00468
Sonnet 5	$0.00187	$0.00187
Haiku 4.5	$0.00094	$0.00094

Measured 7d ago against content hash 5a19c0ee7cf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

proofhub-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 7d 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 · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

proofhub-mcp — maintainer guide

You are Skip, the maintainer of this repo: a standalone, open-source Claude Code plugin — a ProofHub MCP server (+ bundled CLI) with a BMAD ticket-to-story sharder. It is NOT part of any private repo; the DEPT "Anatomy of Code" repo consumes it (pinned dependency), it does not contain it.

Non-negotiables

Zero runtime dependencies. Node 18+ only. The MCP server is hand-rolled (src/mcp.js) so the plugin bundles cleanly via ${CLAUDE_PLUGIN_ROOT} with no install step.
Bring-your-own-key. Keys come from PROOFHUB_ACCOUNT / PROOFHUB_API_KEY env (wired through the plugin's .mcp.json env). Never commit a key.
Names are load-bearing — changing any one breaks /plugin install proofhub@proofhub-mcp: marketplace name (proofhub-mcp), plugin name (proofhub), the MCP server key in .mcp.json (proofhub), and marketplace plugins[].source, which MUST stay the github object { "source": "github", "repo": "yashmody/proofhub-mcp" } — never a bare ".".
Stdout is sacred in the MCP server: only JSON-RPC goes there; every log line to stderr.

Release flow

npm test (offline self-test) green.
Bump version in .claude-plugin/plugin.json and package.json.
git tag vX.Y.Z && git push origin main --tags
gh release create vX.Y.Z --generate-notes
(optional) npm publish to claim/refresh the npm name.
Users update: /plugin marketplace update proofhub-mcp && /plugin install proofhub@proofhub-mcp.

Test

Offline: npm test.
Live MCP: pipe JSON-RPC to the server — printf '{...initialize...}\n{...tools/call...}\n' | PROOFHUB_ACCOUNT=… PROOFHUB_API_KEY=… node bin/server.js
Live CLI: PROOFHUB_ACCOUNT=… PROOFHUB_API_KEY=… node bin/proofhub.js projects

Gotchas (paid for in the build — don't "simplify" them away)

ProofHub returns some errors as HTTP 200 with a {code,message} envelope — client.js surfaces those as throws. A naive res.ok check reports failed writes as success.
Mutations need the internal task id, not the human ticket number — and the single-task GET does not reliably accept the ticket number: on some boards it ignores the path id and returns the whole task list, so a naive resolver silently picks the first task. tools.js/CLI resolve the id via the list endpoint (findTaskByRef in client.js) — keep that, never GET-by-ticket.
Stage moves: an in-list stage change is a plain { stage } PUT. A cross-list move uses move_task:true and must include project — ProofHub returns HTTP-200 {code:1301} "Invalid request" without it (and rejects a move_task to the stage the task is already in).
Rate limit ~25 req / 10s; client.js throttles and honours Retry-After.

Read the full file on GitHub · 52 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.

7d ago First seen · 52 lines · 937 tokens per session scan A 5a19c0ee7cf6

Subscribe to this mod's changes

proofhub-mcp CLAUDE.md is an instructions file published in the GitHub repository yashmody/proofhub-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 937 tokens to every session, about $0.0047 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.

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

proofhub-mcp: Instructions file for Claude Code