agentmods.dev

meshcore-mcp: Instructions file for Claude Code

CLAUDE.md

meshcore-mcp CLAUDE.md is an instructions file for Claude Code from dpup/meshcore-mcp. It costs 522 tokens per session, scanned A, original, MIT.

A project instruction file for Claude Code working on an MCP server that exposes a MeshCore node. It records the architecture, testing commands, coding rules, and issues that must not regress.

In plain words
What is it for?
Use it when changing, testing, building, or checking documentation for dpup/meshcore-mcp. The project uses Bun, TypeScript, Node.js 18 or newer, and an in-memory MCP client for tests.
Why use it?
It tells the coding agent how the server is designed and how to verify changes without breaking its contracts.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is dpup/meshcore-mcp's own configuration. It tells Claude Code how to work on meshcore-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything meshcore-mcp configures →

not rated 2repo 5mo ago A scan 522 tokens original MIT
View source ↗ dpup/meshcore-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to dpup/meshcore-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/dpup/meshcore-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dpup/meshcore-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.

agentmods badge for meshcore-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dpup/meshcore-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/dpup/meshcore-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dpup/meshcore-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dpup/meshcore-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.

agentmods 80×15 button for meshcore-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dpup/meshcore-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dpup/meshcore-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 522 This file is loaded in full into every session.
When invoked 522 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00522 $0.00522
Opus 5.5 $0.00209 $0.00209
Sonnet 5.5 $0.00104 $0.00104
Haiku 4.5 $0.00052 $0.00052

Measured 2mo ago against content hash db81bfddbba2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

meshcore-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 2mo 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 · 38 lines

What it actually says

CLAUDE.md

Project guidance for Claude Code lives in AGENTS.md — read it first. It covers the architecture, the two contracts, conventions, and the don't-regress list.

TL;DR

  • An MCP server exposing a MeshCore node as tools/resources/prompts. Built on @dpup/meshcore-ts; tested/demoed against @dpup/meshcore-sim. Ungated by design — no policy layer (that's meshcore-elmer).
  • MeshService takes an injected MeshCoreClient + Clock. Tests drive a real MCP Client (in-memory transport) → server → sim-backed client.
  • Verify with: bun run typecheck · bun run test · bun run build · bun run docs:check (the generated docs/api.md must stay in sync).
  • ESM-only, Node ≥ 18, NodeNext, verbatimModuleSyntax, strict — .js import extensions, split import type / export type.

Don't-regress (details in AGENTS.md)

  1. Injected MeshCoreClient + Clock; never construct them inside MeshService.
  2. No Date.now()/setTimeout below the entrypoint — use the Clock.
  3. Provenance is structural: verified channelMessage/contactMessage vs. unverified channelData/advert/raw — each event carries decryptVerified.
  4. admin is an enumerated, curated set (execution plan §9) — never free-form; risk tier → annotations is deterministic; dryRun never touches the device.
  5. Annotations are the boundary; structured output + actionable isError results, never raw frames or thrown exceptions.
  6. stdout is the MCP channel; diagnostics to stderr.
  7. docs/api.md is generated (bun run docs) — never hand-edit; drift.test.ts guards both contracts.

Planning docs

  • docs/plans/2026-05-26-initial-prd.md — the PRD (Spec v0.3).
  • docs/plans/2026-05-27-execution-plan.md — milestones M0–M9, the two contracts, and §9 the enumerated admin set.
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. 2mo ago First seen · 38 lines · 522 tokens per session scan A db81bfddbba2

Subscribe to this mod's changes

meshcore-mcp CLAUDE.md is an instructions file published in the GitHub repository dpup/meshcore-mcp (2 stars, last pushed 5mo ago), licensed MIT. It adds 522 tokens to every session, about $0.0021 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 2026-08-31.

LoRAagentaimcpmesh-networkingmeshcore
Related

meshcore-mcp CLAUDE.md compared with instructions from other repositories

meshcore-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
meshcore-mcp CLAUDE.mddpup/meshcore-mcpInstructions file25mo agoMITA522Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot