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.
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.
[](https://agentmods.dev/instructions/pilotwaffle/torqclaw/claude-md)<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>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 5.1 | $0.03928 | $0.03928 |
| Opus 5 | $0.01964 | $0.01964 |
| Sonnet 5 | $0.00786 | $0.00786 |
| Haiku 4.5 | $0.00393 | $0.00393 |
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.
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 (onlyCLAUDE.mdis read). The prior graphify-onlyCLAUDE.mdis preserved atCLAUDE.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
/v1tool 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
- Direct operator instruction in the current session
- This file
- Global
E:\.claude\CLAUDE.md - 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):
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.
- 6d ago First seen · 321 lines · 3,928 tokens per session scan A 2b8978fafeb2
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.
Other instructions, from other repositories
sanction AGENTS.md
AGENTS.md instructions for ericlovold/sanction, covering this is not the next.js you know, sanction — project context for ai sessions, what this is, commands and architecture.
sanction CLAUDE.md
Claude Code instructions for ericlovold/sanction, a project described as: Agent wallet, credential vault, and governance layer for autonomous AI agents.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
remnic AGENTS.md
AGENTS.md instructions for joshuaswarren/remnic, covering remnic - agent guide, architecture boundaries (non-negotiable), upstream references, adapter implementation rules and openclaw compatibility window.
linggen CLAUDE.md
Claude Code instructions for linggen/linggen, covering claude.md, doc and spec, build, test, run, architecture and configuration.