What is QClaw AGENTS.md?

A project instruction file for coding agents working on QuantumClaw, a Node.js AI-agent runtime. It documents the project’s architecture, conventions, and operating instructions.

Use it to understand the startup flow, security, memory, model routing, agent loading, communication channels, dashboard, and command-line code.

It gives agents the context needed to make changes that fit the repository’s modules, coding style, and security design.

QClaw AGENTS.md — Instructions file by QuantumClaw

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/quantumclaw/qclaw/agents-md

Clone the repo

git clone --depth 1 https://github.com/QuantumClaw/QClaw

Made for: Codex, OpenCode.

Per session 595 This file is loaded in full into every session.

When invoked 595 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.

Model	Per session	Once invoked
Fable 5	$0.00595	$0.00595
Opus 5	$0.00298	$0.00298
Sonnet 5	$0.00119	$0.00119
Haiku 4.5	$0.00060	$0.00060

Measured 2d ago against content hash 2be70c7f50b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

QClaw 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 · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — For AI Coding Agents

This file tells AI coding agents (Claude Code, Copilot, Cursor, etc.) how to work on the QuantumClaw codebase.

Project Overview

QuantumClaw (QClaw) is a Node.js AI agent runtime. ESM modules throughout. No TypeScript.

Architecture

src/
├── index.js          # Bootstrap (8-layer startup sequence)
├── credentials.js    # AGEX credential manager (wraps secrets + AGEX SDK)
├── agex-sdk/         # Vendored AGEX SDK (AgexClient, crypto)
├── core/             # Config, logger, heartbeat, delivery queue, completion cache
├── security/         # SecretStore (AES-256-GCM), TrustKernel, AuditLog, approvals
├── memory/           # Cognee knowledge graph + SQLite conversation memory
├── models/           # 5-tier smart router, provider adapters
├── agents/           # Agent registry, personality loading from workspace
├── skills/           # Drop-in markdown skill loader
├── channels/         # Telegram, Discord, Slack, WhatsApp, WebSocket
├── dashboard/        # Express + WS dashboard server
└── cli/              # Onboarding wizard, commands, branding

Conventions

ESM imports (import/export, not require)
British English in docs and comments
No TypeScript
No em dashes in comments or docs
Minimal dependencies (justify any new npm package)
log.info/warn/error/debug/success for logging (not console.log)

Running

npm install
npx qclaw onboard   # first time
npx qclaw start     # run the agent
npx qclaw diagnose  # health check

Testing

npm test                   # runs test suite
npx qclaw diagnose   # runtime health check

Key Patterns

Graceful degradation: If Cognee is down, memory falls back to SQLite. If AGEX Hub is down, credentials fall back to local encrypted secrets. Nothing crashes.
8-layer startup: Security → Memory → Models → Skills → Agents → Channels → Dashboard → Heartbeat. Each layer can fail without killing the rest.
Credential resolution: credentials.get('key') checks AGEX first, then local secrets. Drop-in compatible with SecretStore.
Trust Kernel: VALUES.md defines hard limits. The agent cannot override these. Code that enforces VALUES.md rules should never have a bypass.

Read the full file on GitHub · 66 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.

2d ago First seen · 66 lines · 595 tokens per session scan A 2be70c7f50b6

Subscribe to this mod's changes

QClaw AGENTS.md is an instructions file published in the GitHub repository QuantumClaw/QClaw (53 stars, last pushed 2mo ago), licensed MIT. It adds 595 tokens to every session, about $0.0030 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.

Analytics and metrics Memory and context Security ai-agents openclaw openclaw-plugin openclaw-security

ClawTeam-OpenClaw CLAUDE.md

Instructions for win4r/ClawTeam-OpenClaw, covering claude.md, what this project is, common commands, dev install (from repo root) and cli entry points.

win4r/ClawTeam-OpenClaw · 3,463 tokens

tweetclaw AGENTS.md

Instructions for Xquik-dev/tweetclaw: Each commit must reduce net handwritten source LOC. No exceptions. No one may waive this rule. Additions require larger, useful simplifications elsewhere in this repository. Formatting, minification, generated files, and deleted valuable tests or docs do not count.

Xquik-dev/tweetclaw · 54 tokens

QClaw AGENTS.md