orcbot CLAUDE.md

orcbot CLAUDE.md is an instructions file for coding agents from fredabila/orcbot. It costs 1,690 tokens per session, scanned A, original, MIT.

A repository guide for OrcBot, an autonomous TypeScript AI agent that plans multi-step tasks, uses tools, and delivers results through different channels. It documents the commands, architecture, and file-backed state used by the agent.

In plain words
What is it for?
Building, running, and testing OrcBot, and modifying its command-line interface, agent loop, decision process, skills, or stored state.
Why use it?
It gives contributors a map of the codebase and explains how the agent's planning loop, skills, decision engine, and persistent data fit together.

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/fredabila/orcbot/claude-md
Clone the repo
git clone --depth 1 https://github.com/fredabila/orcbot

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 orcbot CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fredabila/orcbot/claude-md.svg)](https://agentmods.dev/instructions/fredabila/orcbot/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fredabila/orcbot/claude-md"><img src="https://agentmods.dev/badge/instructions/fredabila/orcbot/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,690 This file is loaded in full into every session.
When invoked 1,690 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 $0.01690 $0.01690
Opus 5 $0.00845 $0.00845
Sonnet 5 $0.00338 $0.00338
Haiku 4.5 $0.00169 $0.00169

Measured 3d ago against content hash 1221a8792276, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orcbot 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 · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

npm run build          # tsc compile → dist/ (also copies Chrome CDP files)
npm run build:fast     # esbuild fast bundle (node build.mjs)
npm run dev            # ts-node dev mode
npm test               # vitest run --reporter=dot
npm run test:watch     # vitest watch mode
npm start              # run compiled CLI from dist/

Run a single test file:

npx vitest run tests/decisionEngine.test.ts

Architecture

OrcBot is an autonomous AI agent orchestrator. It plans multi-step tasks using a ReAct loop (Thought→Action→Observation), executes skills (tools), and delivers results over multiple channels. All state is file-backed under ~/.orcbot/ (or ORCBOT_DATA_DIR).

Layer Map

Layer Key File(s) Role
CLI src/cli/index.ts Entrypoint, TUI menus, daemon management
Agent src/core/Agent.ts Main action loop, registers 80+ skills, wires all subsystems
Decision Engine src/core/DecisionEngine.ts Assembles prompt + context, calls LLM, validates response, runs termination review
Simulation src/core/SimulationEngine.ts Pre-plans execution before tools run
Parser src/core/ParserLayer.ts 3-tier fallback: strict JSON → relaxed → regex extraction
Decision Pipeline src/core/DecisionPipeline.ts Post-parse guardrails (dedup, loop detection, frequency limits)
Prompts src/core/prompts/ 8 modular helpers (Core, Tooling, Browser, Research, …); PromptRouter injects only relevant ones
LLM Routing src/core/MultiLLM.ts gemini*→Google, nvidia:*→NVIDIA, bedrock:*→AWS, else OpenAI; auto-fallback
Skills Manager src/core/SkillsManager.ts Skill registry, dynamic plugin loading from ~/.orcbot/plugins/, intent matching
Memory src/memory/MemoryManager.ts Short/episodic/long tiers + vector semantic search
Action Queue src/memory/ActionQueue.ts Priority-sorted durable queue with retry, chaining, TTL
Storage src/storage/JSONAdapter.ts Atomic JSON writes (temp→rename), .bak crash recovery
Channels src/channels/ Telegram (Telegraf), WhatsApp (Baileys), Discord (discord.js), Web Gateway (Express+WS)
Browser src/tools/WebBrowser.ts Playwright + Serper/Google/Bing/DDG search chain, 2Captcha
Config src/config/ConfigManager.ts YAML hot-reload; never hardcode keys — use ConfigManager.get()

Read the full file on GitHub · 152 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 · 152 lines · 1,690 tokens per session scan A 1221a8792276

Subscribe to this mod's changes

orcbot CLAUDE.md is an instructions file published in the GitHub repository fredabila/orcbot (11 stars, last pushed 5mo ago), licensed MIT. It adds 1,690 tokens to every session, about $0.0085 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.