Borrowing it
Nothing to install: this file belongs to pilotwaffle/TORQCLAW. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pilotwaffle/TORQCLAW/master/.claude/agents/README.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/agents/pilotwaffle/torqclaw/readme)<a href="https://agentmods.dev/agents/pilotwaffle/torqclaw/readme"><img src="https://agentmods.dev/badge/agents/pilotwaffle/torqclaw/readme/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/pilotwaffle/torqclaw/readme"><img src="https://agentmods.dev/badge/agents/pilotwaffle/torqclaw/readme.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01320 |
| Opus 5.5 | $0.00000 | $0.00528 |
| Sonnet 5.5 | $0.00000 | $0.00264 |
| Haiku 4.5 | $0.00000 | $0.00132 |
Grade A, and why
README 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 12d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TorqClaw agent routing policy
Adapted from the TORQ Console harness (E:\TORQ-CONSOLE\.claude\agents).
These are TorqClaw-local definitions. The Console harness drives a different
product through .torq/launch/* watcher scripts and hardcoded
E:\TORQ-CONSOLE\... paths; running those agents against this repo would read
specs from and write verdicts into the wrong product. What is ported here is the
discipline, re-pathed to E:\TorqClaw.
Roles and model assignments (operator-set 2026-08-09; model map reconciled to CLAUDE.md §2, operator-updated 2026-08-12)
Authoritative source for the role/model map is TORQCLAW
CLAUDE.md§2. This table mirrors it. Supersession (2026-08-12): G1R moved from Opus 4.7 to Opus 5; historical gate records referencing 4.7 are not retroactively invalidated.
| Role | Model | Model ID | Responsibility |
|---|---|---|---|
| G1D / planner / router | Fable-5 | claude-fable-5 |
Orchestrate. Scope the ticket, route work, hold the sequence. Does not implement. |
| G1R / reviewer | Opus 5 | claude-opus-5 |
Independent review when design, architecture, risk, or security is involved. Reviews the SPEC before the Builder spends compute. |
| Builder | Sonnet 5 | claude-sonnet-5 |
Implement the spec precisely. Does not design or approve. |
| RB / alternate debug worker | GLM-5.2 | (if available) | Scout, triage, debug, propose. Never final authority. Code touching routing, approval gates, cost enforcement, secrets, production config, or path scoping must be reviewed by Opus 4.8 (G2A). |
| G2A / final verifier | Opus 4.8 | claude-opus-4-8 |
Grade high-impact changes against files, tests, build output, git state, and acceptance criteria. Sole authority to authorize a push. |
| Cheap verification | Haiku 4.5 / fast | claude-haiku-4-5 |
Checklist grading, log triage, scope sanity checks. Never sole final authority for risky code, merges, security, production, or architecture. |
| Memory-writer | — | Updates STATE.md / MEMORY.md only after meaningful progress, tests pass, and verifier/G2A passes. |
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.
- 12d ago Changed · +3 lines 4912d1ab94d9
- 2mo ago First seen · 78 lines · 0 tokens per session scan A a781d3c65c47
README is an agent published in the GitHub repository pilotwaffle/TORQCLAW (8 stars, last pushed 12d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,320 tokens. 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.
README compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| READMEpilotwaffle/TORQCLAW | Agent | 8 | 12d ago | Apache-2.0 | A | 0 | Claude Code |
| penalistacapazme/mcp-legal-it | Agent | 30 | 3d ago | Apache-2.0 | A | 38 | Claude Code |
| yinyuelinggen/linggen | Agent | 11 | yesterday | Apache-2.0 | A | 43 | Claude Code |
| Patronus Securitytenable/cyberagents-exchange | Agent | 23 | yesterday | none | A | 27 | Claude Code |
| memory-curatorkostya-pakhomov/graphmind | Agent | 2 | 3mo ago | MIT | A | 45 | Claude Code |
| gsd-intel-updatermrboups/xbrain | Agent | 2 | 1mo ago | MIT | A | 22 | Claude Code |
| gsd-research-synthesizermrboups/xbrain | Agent | 2 | 1mo ago | MIT | A | 37 | Claude Code |