What is mcp-signal CLAUDE.md?

Repository instructions for mcp-signal, a small TypeScript library that records usage events in MCP widgets and sends them to configurable destinations.

They guide agents when testing, type-checking, formatting, building, and checking the package before a commit.

They explain the project’s structure and manual checks, reducing the chance of breaking its packages, bundles, or supported build formats.

How Roee-Tsur/mcp-signal configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Roee-Tsur/mcp-signal. 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/Roee-Tsur/mcp-signal/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Roee-Tsur/mcp-signal

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/roee-tsur/mcp-signal/claude-md/github.svg)](https://agentmods.dev/instructions/roee-tsur/mcp-signal/claude-md)

Your own site

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

Per session 2,550 This file is loaded in full into every session.

When invoked 2,550 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	$0.02550	$0.02550
Opus 5.5	$0.01020	$0.01020
Sonnet 5.5	$0.00510	$0.00510
Haiku 4.5	$0.00255	$0.00255

Measured 2mo ago against content hash 50a7faa62293, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-signal 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 · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code (and other AI agents) working in this repo. Terse and directive by design; see README.md + docs/ for the human narrative.

What this is

mcp-signal — a tiny, zero-runtime-dependency TypeScript telemetry SDK that runs inside MCP widgets (Claude MCP Apps, ChatGPT Apps SDK, mcp-ui) and forwards usage events to any destination via a pluggable adapter. Published on npm as mcp-signal.

Commands

npm test              # vitest (jsdom) — 122 tests
npm run test:coverage # v8 coverage (~97%)
npm run typecheck     # tsc --noEmit
npm run build         # tsup -> dist/ : ESM + CJS + IIFE + .d.ts
npm run format        # prettier --write  (format:check to verify)
npm run check:bundle  # assert no server code leaked into the widget bundles (needs a build)
npm run check:package # publint --strict && attw --pack . (exports map resolves for every mode)
npm run example       # build, then serve the demo at http://localhost:8787

Before committing, run: npm run typecheck && npm test && npm run format:check. There is no pre-commit hook — this gate is manual, but GitHub Actions CI (.github/workflows/ci.yml) runs it on every push/PR (tests on Node 18/20/22, plus typecheck + format:check + build + check:bundle + check:package). prepublishOnly enforces the same gate on publish.

Architecture — destinations × transports, one contract

Two orthogonal ideas joined by a single interface:

Destination adapters (where events land): consoleAdapter, webhookAdapter, posthogAdapter. The same contract runs client-side or server-side.
Transports (how a batch leaves the widget):
1. Bridge (recommended) — bridgeAdapter hands each batch to an app-only MCP tool via the host (window.openai.callTool / a tools/call postMessage); your server runs createSignalReceiver. Bypasses CSP, model-invisible.
2. Direct HTTP — posthogAdapter/webhookAdapter POST from the widget (needs a CSP allowlist).
3. Console — local dev.

Read the full file on GitHub · 160 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.

2mo ago First seen · 160 lines · 2,550 tokens per session scan A 50a7faa62293

Subscribe to this mod's changes

mcp-signal CLAUDE.md is an instructions file published in the GitHub repository Roee-Tsur/mcp-signal (2 stars, last pushed 3mo ago), licensed MIT. It adds 2,550 tokens to every session, about $0.0102 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.

Analytics and metrics apps-sdk chatgpt-apps claude event-tracking instrumentation

mcp-signal CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-signal CLAUDE.mdRoee-Tsur/mcp-signal	Instructions file	2	3mo ago	MIT	A	2,550	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-signal: Instructions file for Claude Code