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/pilotwaffle/torqclaw/agents-mdgit clone --depth 1 https://github.com/pilotwaffle/TORQCLAWWrote 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/agents-md)<a href="https://agentmods.dev/instructions/pilotwaffle/torqclaw/agents-md"><img src="https://agentmods.dev/badge/instructions/pilotwaffle/torqclaw/agents-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 | $0.00669 | $0.00669 |
| Opus 5 | $0.00334 | $0.00334 |
| Sonnet 5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
TORQCLAW 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 4d 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Rooms UI lane (worktree rooms-ui, branch rooms-ui-phase0)
This worktree is the only place Rooms UI work happens. Do not edit the main checkout at E:\TorqClaw from this lane, and do not run this lane's sessions with full-access/auto-approve in E:\.claude or E:\TorqClaw.
The job
Build Torq Rooms Phase 0 per docs/PRD-TCLAW-ROOMS-UI-PHASE0.md and the approved Gate 1 packet.
docs/PRD-TCLAW-ROOMS-UI-008.md is a historical/superseded stub and is not build authority.
Phase 0 is a reversible Room shell and product-label pass over existing console facts. It is not a new authority plane. Do not add Room-local approvals, receipts, budgets, agent management, schedules, export-policy mutation, message composer, ACK behavior, Web Locks/IndexedDB ledger, gateway correlation substitutes, or client-side operation recovery from this lane unless a later gated packet explicitly authorizes it.
Hard boundaries
- UI-first lane. Prefer data the gateway already serves. If a slice needs a gateway/contract change, stop and file it; that change ships from the main lane first, then this branch rebases onto it. Do not fork contracts, authz, store, or dispatcher logic here.
- No approval/budget/receipt bypass. Bots never send external messages or write files outside the existing approval path. Never weaken member-payload key-set tests.
- Room current-session evidence is rendering/navigation only. Room spend caps, per-room allowed tools/path scope, in-room approval decisions, and Room-local write controls are deferred unless a later gated packet authorizes them.
- No Slack/Discord/X adapters. No new dependencies without saying so first. No secrets in code, logs, or commits; the repo is public.
- Follow repo conventions: pnpm + turbo. Gates before done:
pnpm typecheck,pnpm test,pnpm build,pnpm --filter @torqclaw/contracts check,pnpm reachabilitywhen available and relevant. Two tests are known load-sensitive:tests/collab-build-lock.test.ts,tests/failover/*cold-start; rerun isolated before calling them regressions. - Commit on this branch only. No push/merge to master from this lane without the operator's explicit go. Merges happen rebased, with a
git diff --stat origin/master...HEADdeletion audit of zero. - Governed multi-model work uses packet handoffs in
E:\.claude\model-handoff\rooms-ui-phase0-implementation-20260824\, fresh threads per seat, and the operator's OpenAI-only routing instructions.
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.
- 4d ago First seen · 27 lines · 669 tokens per session scan A b8e577df0b84
TORQCLAW AGENTS.md is an instructions file published in the GitHub repository pilotwaffle/TORQCLAW (4 stars, last pushed 10d ago), licensed Apache-2.0. It adds 669 tokens to every session, about $0.0033 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.
basic-memory CLAUDE.md
Claude Code instructions for basicmachines-co/basic-memory, a project described as: AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN.