signalgrid-mcp: Instructions file for Claude Code

CLAUDE.md

signalgrid-mcp CLAUDE.md is an instructions file for Claude Code from DanFashauer/signalgrid-mcp. It costs 1,687 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP server that reads trust signals from a Mac and can produce a device-level security verdict. MCP is a way for an AI tool to call software tools and receive their results.

In plain words
What is it for?
Use it when changing or reviewing the server, its Mac posture checks, its trust verdict, its documentation, or its runbook.
Why use it?
It tells contributors how to preserve the server's security rules, document its tools, and distinguish local device findings from a broader access decision.

Instructions file for Claude Code

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

This is DanFashauer/signalgrid-mcp's own configuration. It tells Claude Code how to work on signalgrid-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 signalgrid-mcp configures →

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/danfashauer/signalgrid-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/danfashauer/signalgrid-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,687 This file is loaded in full into every session.
When invoked 1,687 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 $0.01687 $0.01687
Opus 5.5 $0.00675 $0.00675
Sonnet 5.5 $0.00337 $0.00337
Haiku 4.5 $0.00169 $0.00169

Measured 18d ago against content hash 53714bbf11f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

signalgrid-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 18d 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 · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — signalgrid-mcp

Guidance for owner-authorized agents and humans working in this repository. Read it before your first change. These rules override default behaviour.

What this is

An MCP server that exposes macOS-native device trust signals — the facts about a Mac that no Linux container or cloud runner can gather. It is one source feeding SignalGrid's decision core; the core and the canonical posture contract live in the SignalGrid-Review-Hub repository. README.md must list every registered tool; RUNBOOK.md says how it is run and verified.

Role: read the device and report honestly. Almost every tool only reports posture. One piece here does decide: src/signalgrid_mcp/tools/verdict.py folds a posture report into a single-device verdict (two or more criticals deny, one restricts, unmanaged / auto-update off / any unknown steps up, else allow). It ships as the tool signalgrid_trust_verdict, the resource signalgrid://verdict and the posture report's include_verdict. Its own _note says it is a local, single-device verdict that the SignalGrid fabric fuses with identity, custody and other signals for the final decision. The golden rules below bind it.

Both SignalGrid lanes (Mac and cloud) have opened pull requests here. Work arrives as an explicitly selected pull request with its reason in the body.

Golden rules — do not break these

  1. Strictly read-only. No tool mutates the device, ever: no writes to files, settings, profiles, users, services or the network. Every tool carries the read-only annotation; a tool without it does not ship. A new tool that needs a write is a different product and needs a decision record in the Review-Hub first.
  2. Unknown is unknown, and never loosens an answer. A value this server could not determine is reported as null/unknown, never as "off", "disabled" or "safe". Downstream, unknown raises the bar; a collector that guesses lowers it, which is the one failure SignalGrid refuses. This binds verdict.py too: compute_verdict stays pure and deterministic (no clock, randomness or I/O), and a control it cannot read raises the answer to at least step_up, never allow. Some probes legitimately read unknown without elevation or Full Disk Access (profiles list, systemsetup, tmutil latestbackup; README "Permissions & elevation", RUNBOOK step 3 item 2), by design. An unknown on a real Mac is a discrepancy to chase, neither a fact nor automatically a bug: if the raw command shows a value, the parser is wrong. Never "fix" an unknown by running elevated or by inferring a value.
  3. The contract is owned elsewhere. The canonical posture contract is lib/integrations/src/integrations/macos-posture/contract/posture-report.contract.json in the Review-Hub. tests/test_posture_contract.py reads it through SIGNALGRID_CONTRACT_PATH only when that variable is set, which the Review-Hub's pnpm run verify:all does. Without it (this repository's CI) the test checks a copy of the core shape built into the test file. Keep that copy equal to the contract, never ahead of it: a shape change is a Review-Hub change first, proven with verify:all, then this repository follows.
  4. Truthful on CI. Ubuntu CI proves the code, not the signals. verify.sh installs, runs pytest -q (on a Mac that includes the live collector tests), then tools/inspect_stdio.py, which rejects crashes, missing tools, MCP tool errors and missing read-only markers. Honest unknown results can still pass protocol health. Its value/unknown column uses text-marker heuristics and is not proof that a signal is live. The test-macos CI job runs pytest -q on GitHub's macOS runner. Live assertions are in tests/test_live_collectors.py and Darwin-only checks in tests/test_smoke.py; these do not prove every collector reads a value. A green ubuntu run is never evidence that a collector works.
  5. Nothing ships by assertion. README.md must list and describe every registered tool (git grep 'name="signalgrid_' src/ is the list; EXPECTED_TOOLS in tests/test_smoke.py must match it). CHANGELOG.md is meant to describe what shipped, so do not use it as the tool list. A capability is claimed only after successful, signal-specific returned data or a corresponding live-collector assertion establishes it on a real Mac. An inspector label, registration or green ubuntu run is not that proof.

Read the full file on GitHub · 116 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. 18d ago First seen · 116 lines · 1,687 tokens per session scan A 53714bbf11f6

Subscribe to this mod's changes

signalgrid-mcp CLAUDE.md is an instructions file published in the GitHub repository DanFashauer/signalgrid-mcp (0 stars, last pushed 19d ago), licensed MIT. It adds 1,687 tokens to every session, about $0.0067 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 2026-10-30.

Related

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

signalgrid-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
signalgrid-mcp CLAUDE.mdDanFashauer/signalgrid-mcpInstructions file019d agoMITA1,687Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot