Borrowing it
Nothing to install: this file belongs to jiridudekusy/signal-cli-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.
curl -O https://raw.githubusercontent.com/jiridudekusy/signal-cli-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/jiridudekusy/signal-cli-mcpWrote 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.
[](https://agentmods.dev/instructions/jiridudekusy/signal-cli-mcp/claude-md)<a href="https://agentmods.dev/instructions/jiridudekusy/signal-cli-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jiridudekusy/signal-cli-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.
<a href="https://agentmods.dev/instructions/jiridudekusy/signal-cli-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jiridudekusy/signal-cli-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00818 | $0.00818 |
| Opus 5 | $0.00409 | $0.00409 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
signal-cli-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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
signal-cli-mcp — guide for AI assistants
Architecture
The project is divided into layers. Each layer depends only on the layers below it:
src/index.ts — entrypoint: wires all layers together
src/mcp-server.ts — MCP tools (proposeSignal*); resolves the target, then calls approval-core + signal-client
src/contact-resolver.ts — resolves contact name <-> number and group name <-> id (reads signal-cli, cached)
src/gui-server.ts — HTTP server for the approval GUI (SSE + POST); calls approval-core
src/notifier.ts — optional ntfy push on each new proposal (fire-and-forget; Click + Approve/Reject actions; listens to approval-core 'proposal')
src/approval-core.ts — proposal state machine (in-memory, no DB); emits 'proposal' and 'update'
src/signal-client.ts — client for signal-cli-rest-api (send + read-only contact/group lookups)
src/config.ts — loads configuration from env variables
Tests live in test/ and mirror the modules (1:1).
Security invariant
No tool may send a message without approval. All sending goes exclusively through signal-client.ts and is called only after Decision.approved === true in approval-core.ts.
This is a structural guarantee, not a convention: the send methods (sendMessage, sendGroupMessage, createGroup) are only reached from mcp-server.ts after await decision with an approved result. If the user rejects or the timeout expires, no send method is called. SignalClient also exposes read-only lookups (listContacts, listGroups) used by contact-resolver.ts for name resolution and GUI display — these grant no ability to send and are not exposed as MCP tools.
Recipient resolution
mcp-server.ts resolves every target through contact-resolver.ts before creating the proposal: a recipient/member may be a contact name or an E.164 number; a group target may be a group name or group.<id>. Name matching is exact (case-insensitive, trimmed); zero or multiple matches throw (surfaced to the LLM as failed: … with candidates). The resolved Name (number) label is stored on the proposal and shown in the GUI so the human verifies the real identity.
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.
- 9d ago First seen · 47 lines · 818 tokens per session scan A 6391d804ef13
signal-cli-mcp CLAUDE.md is an instructions file published in the GitHub repository jiridudekusy/signal-cli-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 818 tokens to every session, about $0.0041 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.
Other instructions, from other repositories
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.
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.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.