FastClaw AGENTS.md

A guide for FastClaw, a Slack and Telegram bot backed by an autonomous coding agent and an administration dashboard.

In plain words
What is it for?
Use it when changing task handling, the SQLite database, Slack or Telegram integrations, the admin UI, or the Railway deployment.
Why use it?
It explains the project structure and deployment setup so agents can work in the correct Rust server, React dashboard, and supporting services.

Instructions file for CodexOpenCode

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/grail-computer/fastclaw/agents-md
Clone the repo
git clone --depth 1 https://github.com/Grail-Computer/FastClaw

Made for: Codex, OpenCode.

Per session 2,029 This file is loaded in full into every session.
When invoked 2,029 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 $0.02029 $0.02029
Opus 5 $0.01014 $0.01014
Sonnet 5 $0.00406 $0.00406
Haiku 4.5 $0.00203 $0.00203

Measured 2d ago against content hash 7d98485121cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

FastClaw AGENTS.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.

AGENTS.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — FastClaw

What This Is

FastClaw is a Slack/Telegram bot backed by an autonomous AI agent (OpenAI Codex CLI). It receives messages from Slack or Telegram, queues them as tasks in a SQLite database, runs Codex in a sandboxed subprocess to produce answers, and posts the results back. It ships with an admin dashboard for configuration, monitoring, and approvals.

Production deployment: Railway (Docker).


Repo Layout

FastClaw/
├── grail/                      # Main Rust workspace (this is the product)
│   ├── Cargo.toml              # Workspace root
│   └── crates/
│       ├── grail-server/       # Core: web server, worker, admin UI, DB
│       │   ├── src/            # All Rust source (see below)
│       │   ├── (no templates)
│       │   └── migrations/     # SQLite migrations (applied on startup)
│       ├── grail-slack-mcp/    # MCP tool server for Slack API
│       └── grail-web-mcp/     # MCP tool server for Brave search + web fetch
├── frontend/                    # React admin dashboard source
├── codex/                      # Vendored OpenAI Codex CLI (Git submodule)
├── guardrails/                 # Vendored Guardrails AI library (Git submodule)
├── nanobot/                    # Vendored Nanobot agent (Git submodule)
├── coworker/                   # Coworker agent (Git submodule)
├── Dockerfile                  # Multi-stage: build Rust → Debian slim + Codex CLI
├── entrypoint.sh               # Drops privileges, runs grail-server
├── railway.json                # Railway deploy config (Dockerfile builder, healthcheck)
├── slack-app-manifest.yaml     # Slack app scopes and event subscriptions
└── .env.example                # All supported environment variables

Source Files (grail/crates/grail-server/src/)

File Purpose
main.rs Axum web server, /admin React SPA serving, admin JSON API mount, Slack/Telegram webhooks, health, Slack signature verification
worker.rs Background task processor: claims tasks, builds Codex prompts, spawns Codex CLI subprocess, parses agent output, sends replies
db.rs All SQLite operations (settings CRUD, task queue, sessions, cron, guardrails, approvals, secrets)
models.rs Shared structs (Task, Session, Settings, etc.)
slack.rs SlackClient — post messages, upload files, download files, fetch channel history
telegram.rs Telegram webhook payload types and message-sending client
codex.rs Codex CLI subprocess management: spawn, stream output, parse structured responses
codex_login.rs ChatGPT device login / OAuth flow for Codex authentication
approvals.rs Approval request lifecycle (create, decide, check)
config.rs CLI args via clap (--port, --data-dir, etc.)
crypto.rs AES-GCM encryption/decryption for stored secrets
secrets.rs Secret retrieval (env vars → encrypted SQLite fallback)
guardrails.rs Apply guardrail rules to shell commands before execution
cron_expr.rs Cron expression parsing helpers
bootstrap.rs First-run setup and data directory initialization

Read the full file on GitHub · 192 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. 2d ago First seen · 192 lines · 2,029 tokens per session scan A 7d98485121cf

Subscribe to this mod's changes

FastClaw AGENTS.md is an instructions file published in the GitHub repository Grail-Computer/FastClaw (11 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 2,029 tokens to every session, about $0.0101 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 2026-08-30.

Related

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

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.

vercel/next.js · 7,296 tokens