RustifyMyClaw CLAUDE.md

RustifyMyClaw CLAUDE.md is an instructions file for coding agents from Escoto/RustifyMyClaw. It costs 2,935 tokens per session, scanned A, original, Apache-2.0.

Project instructions for a Rust daemon that connects messaging platforms to local AI command-line tools. They describe its files, modules, configuration, security checks, and code rules.

In plain words
What is it for?
Use them when working on RustifyMyClaw, especially for locating modules, understanding startup and configuration, or following build and coding conventions.
Why use it?
They give an agent the project structure and rules it needs before changing code, reducing guesses about where logic belongs and how the program should behave.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/escoto/rustifymyclaw/claude-md
Clone the repo
git clone --depth 1 https://github.com/Escoto/RustifyMyClaw

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 RustifyMyClaw CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/escoto/rustifymyclaw/claude-md.svg)](https://agentmods.dev/instructions/escoto/rustifymyclaw/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/escoto/rustifymyclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/escoto/rustifymyclaw/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,935 This file is loaded in full into every session.
When invoked 2,935 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02935 $0.02935
Opus 5 $0.01468 $0.01468
Sonnet 5 $0.00587 $0.00587
Haiku 4.5 $0.00294 $0.00294

Measured 3d ago against content hash e3bc9dbdbe00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

RustifyMyClaw 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 3d 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 · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — RustifyMyClaw

Project

Rust daemon bridging messaging platforms to local AI CLI tools. See docs/architecture.md for architecture and component specs.

Module Layout

File Purpose
src/main.rs Entrypoint. Loads config, calls orchestration helpers from startup.rs.
src/startup.rs Startup orchestration: signal handler, rate limiter, workspace/backend/provider construction, router and provider spawning, config watcher, shutdown sequencing.
src/types.rs All canonical types: ChatId, ChannelKind, AllowedUser, InboundMessage, MessageContext, WorkspaceHandle, CliResponse, SessionState, FormattedResponse, ResponseChunk.
src/config.rs AppConfig struct hierarchy, YAML parsing, ${VAR} env var interpolation, resolve_path(), validate(), effective_output_config(), diff_reload(), warn_misplaced_fields().
src/config_reload.rs notify-based file watcher. Debounced 300ms. Calls load_from_path() + diff_reload() + callback on change.
src/security.rs SecurityGateHashSet<String> of resolved user IDs, is_allowed() check. One instance per channel.
src/session.rs SessionStoreHashMap<ChatId, SessionState>, should_continue(), mark_active(), reset().
src/router.rs Pipeline hub. Receives InboundMessage via mpsc, parses BridgeCommand, handles commands, dispatches prompts to executor, applies rate limiting, sends responses.
src/executor.rs Spawns CLI via tokio::process::Command. Wraps stdout/stderr capture with timeout. Returns CliResponse.
src/formatter.rs Chunks output (Natural/Fixed strategies). char_boundary_floor() for UTF-8 safety. File upload above threshold.
src/rate_limit.rs Per-user sliding window. HashMap<String, VecDeque<Instant>> behind Mutex. Returns Allowed or LimitedFor(Duration).
src/command/mod.rs BridgeCommand enum: Prompt, NewSession, Status, Help, UseWorkspace. parse() method.
src/backend/mod.rs CliBackend trait + build() factory.
src/backend/claude.rs ClaudeCodeBackend: claude -p "<prompt>", -c for session continuation.
src/backend/codex.rs CodexBackend: codex -q "<prompt>". No session continuation.
src/backend/gemini.rs GeminiBackend: gemini -p "<prompt>" -y. No session continuation.
src/channel/mod.rs ChannelProvider trait.
src/channel/telegram.rs TelegramProvider — teloxide long-polling.
src/channel/whatsapp.rs WhatsAppProvider — axum webhook + reqwest Graph API.
src/channel/slack.rs SlackProvider — Socket Mode WebSocket via tokio-tungstenite.
src/tests/ All test files, referenced from source via #[path = "tests/..."].
choco/ Chocolatey package: rustifymyclaw.nuspec, install/uninstall scripts.
.github/workflows/ci.yml CI: fmt, clippy, test on push/PR.
.github/workflows/release.yml Release: version bump, cross-platform build, GH Release, then calls publish.yml.
.github/workflows/publish.yml Reusable workflow (workflow_call): parallel crates.io + Chocolatey publish.

Read the full file on GitHub · 162 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. 3d ago First seen · 162 lines · 2,935 tokens per session scan A e3bc9dbdbe00

Subscribe to this mod's changes

RustifyMyClaw CLAUDE.md is an instructions file published in the GitHub repository Escoto/RustifyMyClaw (8 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 2,935 tokens to every session, about $0.0147 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.