Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/msg43/imessage_mcp/claude-mdgit clone --depth 1 https://github.com/msg43/imessage_mcpWhat 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 | $0.01172 | $0.01172 |
| Opus 5 | $0.00586 | $0.00586 |
| Sonnet 5 | $0.00234 | $0.00234 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
imessage_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 2d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
imessage-index
A local-first iMessage retrieval system: full corpus indexed locally, with a filtered subset exportable to an enterprise search index.
This repo is public-safe by construction
The single rule that governs everything here. This repo is intended to be published. It must never contain:
- Real names, phone numbers, email addresses, hostnames, project ids, bucket names, or business names — in code, comments, tests, fixtures, docstrings, or example config. Use fictional personas (Alice, Bob, Acme Construction) exclusively.
- Credentials of any kind. Secrets come from the OS keychain or the environment, never from a file in either repo.
- Instance configuration. Real values live in a separate private
overlay that the core reads at runtime;
config.example.yamlships here with placeholders only.
If you are reading from a private design document to implement something, carry the design across and not the examples — those documents contain real names by design. Sweep before committing.
Non-negotiables
- Never write to the live
chat.db. Snapshot via SQLite's online-backup API; nevercp(WAL correctness). All derived state lives elsewhere. - All derived state under
data_root, on the encrypted volume. Startup gates on the mount. - Identity resolution precedes segmentation. Nothing downstream
keys on a raw handle; everything keys on
person_id. - Subject validation on the public surface is the only access control. Fail closed. No configuration path disables it. Audience validation and subject validation are not redundant — subject answers "is this the owner?", audience answers "was this token minted for this system?", and only both together stop cross-application replay.
- Default deny on export. Group threads require every participant allowlisted; attachments are gated separately from text bodies.
- The Postgres instance is dedicated. Verified by a two-sided cluster fingerprint with no bypass.
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.
- 2d ago First seen · 108 lines · 1,172 tokens per session scan A 9a05cefa1b82
imessage_mcp CLAUDE.md is an instructions file published in the GitHub repository msg43/imessage_mcp (0 stars, last pushed 15d ago), licensed MIT. It adds 1,172 tokens to every session, about $0.0059 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
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.