TORQCLAW CLAUDE.md

TORQCLAW CLAUDE.md is an instructions file for Claude Code from pilotwaffle/TORQCLAW. It costs 3,928 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for TORQCLAW, a software system that routes tasks between local and cloud-based AI engines through a shared tool bridge. It also defines project context, instruction precedence, and how to check whether the documentation matches the code.

In plain words
What is it for?
Guiding work in the TORQCLAW TypeScript and Python monorepo. A monorepo is one repository containing multiple related applications and packages.
Why use it?
It gives the coding agent consistent rules and warns it to report conflicts when the documented repository structure is outdated.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; positional $N argument.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is cd ../...

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

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 TORQCLAW CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pilotwaffle/torqclaw/claude-md.svg)](https://agentmods.dev/instructions/pilotwaffle/torqclaw/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/pilotwaffle/torqclaw/claude-md"><img src="https://agentmods.dev/badge/instructions/pilotwaffle/torqclaw/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,928 This file is loaded in full into every session.
When invoked 3,928 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 5.1 $0.03928 $0.03928
Opus 5 $0.01964 $0.01964
Sonnet 5 $0.00786 $0.00786
Haiku 4.5 $0.00393 $0.00393

Measured 6d ago against content hash 2b8978fafeb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

TORQCLAW 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 6d 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 · 321 lines

How it starts

The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — TORQCLAW

This file replaces TORQCLAW_CLAUDE.md, which Claude Code never auto-loaded (only CLAUDE.md is read). The prior graphify-only CLAUDE.md is preserved at CLAUDE.md.graphify-orig.bak; its content is now the "Graphify" section below.

1. Repo Context

Address the operator as King Flowers.

TORQCLAW is a hybrid AI orchestrator:

  • TypeScript control plane — gateway, router, MCP bridge, HTTP/channel adapters, console UI
  • Python Hermes execution engine — vendored Hermes agent wrapped by engines/hermes_kernel/mcp_wrapper/
  • Local edge tier — Ollama /v1 tool loop for private / low-complexity / local-only tasks
  • Frontier tier — Hermes engine for complex / research / cloud-allowed tasks
  • Universal MCP bridge — namespaced MCP tools, task-filtered exposure, approval-gated writes

Package manager is pnpm with a Turbo monorepo (apps/*, packages/*, engines/*). Root package is torqclaw-monorepo.

Staleness check: before starting work, verify this context against package.json, pnpm-workspace.yaml, turbo.json, recent commits, and live entrypoints. If this file disagrees with the code, stop and report the conflict before changing architecture-level behavior.

This repo is not TORQ Console and is not the TORQ V5/V6 harness lane.

Instruction precedence

  1. Direct operator instruction in the current session
  2. This file
  3. Global E:\.claude\CLAUDE.md
  4. General Claude Code defaults

Global rules win where they are more restrictive on safety, secrets, destructive commands, untracked files, or owner-gated actions.

Non-TORQ boundary

  • Do not touch E:\TORQ-CONSOLE.
  • Do not touch TORQ Console torq_mmh/.
  • Do not switch into TORQ V5/V6 harness mode.
  • Do not use TORQ Console live harness owner state as authority for this repo.
  • Do not modify unrelated projects, global memory, or global hooks unless explicitly instructed.

2. Governing Harness

Role map (aligned to the global contract in E:\.claude\CLAUDE.md, operator-updated 2026-08-12):

Read the full file on GitHub · 321 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. 6d ago First seen · 321 lines · 3,928 tokens per session scan A 2b8978fafeb2

Subscribe to this mod's changes

TORQCLAW CLAUDE.md is an instructions file published in the GitHub repository pilotwaffle/TORQCLAW (4 stars, last pushed 11d ago), licensed Apache-2.0. It adds 3,928 tokens to every session, about $0.0196 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.