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/escoto/rustifymyclaw/claude-mdgit clone --depth 1 https://github.com/Escoto/RustifyMyClawWrote 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/escoto/rustifymyclaw/claude-md)<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>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 | $0.02935 | $0.02935 |
| Opus 5 | $0.01468 | $0.01468 |
| Sonnet 5 | $0.00587 | $0.00587 |
| Haiku 4.5 | $0.00294 | $0.00294 |
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.
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 |
SecurityGate — HashSet<String> of resolved user IDs, is_allowed() check. One instance per channel. |
src/session.rs |
SessionStore — HashMap<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. |
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.
- 3d ago First seen · 162 lines · 2,935 tokens per session scan A e3bc9dbdbe00
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.
Other instructions, from other repositories
ssbnk AGENTS.md
AGENTS.md instructions for delorenj/ssbnk, covering screenshot bank (ssbnk), project overview, core components, 1) watcher (/watcher) and 2) management ui (/ui).
ssbnk CLAUDE.md
Claude Code instructions for delorenj/ssbnk, a project described as: Lightweight screenshot/gif server built for frictionless, agent-agnostic LLM consumption.
ssbnk GEMINI.md
Gemini CLI instructions for delorenj/ssbnk, a project described as: Lightweight screenshot/gif server built for frictionless, agent-agnostic LLM consumption.
agentgram CLAUDE.md
Instructions for agentgram/agentgram, covering claude.md — agentgram development guide, project overview, tech stack, monorepo structure and core architecture patterns.
cairn CLAUDE.md
Instructions for zilet/cairn, covering claude.md, what cairn is, commands, hard requirements and the traps that actually bite.
mcpelevator CLAUDE.md
Instructions for pacnpal/mcpelevator, covering commands, architecture, conventions, agent skills and issue tracker.