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/fredabila/orcbot/claude-mdgit clone --depth 1 https://github.com/fredabila/orcbotWrote 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/fredabila/orcbot/claude-md)<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>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 | $0.01690 | $0.01690 |
| Opus 5 | $0.00845 | $0.00845 |
| Sonnet 5 | $0.00338 | $0.00338 |
| Haiku 4.5 | $0.00169 | $0.00169 |
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.
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() |
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 · 152 lines · 1,690 tokens per session scan A 1221a8792276
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.
Other instructions, from other repositories
xi AGENTS.md
AGENTS.md instructions for MairwunNx/xi: Communicate with user in preferly in russian language, but you can thinking in american english. For chatting you can use emoji.
workflow AGENTS.md
AGENTS.md instructions for vercel/workflow, covering agent instructions, architecture, core components, workflow execution model and development commands.
gptme AGENTS.md
AGENTS.md instructions for gptme/gptme, covering agent instructions for gptme, git workflow, code style, testing and project structure.
nullclaw CLAUDE.md
Instructions for nullclaw/nullclaw, covering claude.md, mandatory reference, build & test commands, requires exactly zig 0.16.0 (verify: zig version) and build flags.
openclaw CLAUDE.md
Claude Code instructions for openclaw/openclaw, a project described as: Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞.
OwnPilot AGENTS.md
Instructions for ownpilot/OwnPilot, covering ownpilot, architecture, key patterns, commands and tech stack.