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 skills add Megaprompting/torque-loop --skill loopgit clone --depth 1 https://github.com/Megaprompting/torque-loopWrote 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/skills/megaprompting/torque-loop/loop)<a href="https://agentmods.dev/skills/megaprompting/torque-loop/loop"><img src="https://agentmods.dev/badge/skills/megaprompting/torque-loop/loop/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/skills/megaprompting/torque-loop/loop"><img src="https://agentmods.dev/badge/skills/megaprompting/torque-loop/loop.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 | $0.00076 | $0.00748 |
| Opus 5.5 | $0.00030 | $0.00299 |
| Sonnet 5.5 | $0.00015 | $0.00150 |
| Haiku 4.5 | $0.00008 | $0.00075 |
Grade A, and why
loop 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 1mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ratchet:loop — recursive advancement
One pass rarely finishes anything. This command repeats the core cycle until the artifact actually holds under attack. It is the closest thing Ratchet has to a software-quality agent: discover the missing thing, build it, try to break it, fix what broke, serialize.
Step 0 — Load state
ratchet status
ratchet score confidence
The cycle (repeat until the stop condition holds)
Each iteration:
- Discover the missing thing. The highest-leverage gap right now — an untested
assumption, an open defect, a missing piece of the artifact. (Borrow
/ratchet:cutand/ratchet:auctionlogic to pick it.) - Build the artifact or the fix (
/ratchet:build). - Attack it with the five-voice board (
/ratchet:attack); record defects. - Patch only what failed (
/ratchet:patch); resolve the original defect with evidence. - Verify bound to the artifact (
/ratchet:verify); on green,ratchet artifact close <id>. - Compile the advance (
/ratchet:compile); recompute confidence.
The cycle is build → attack → patch → verify → compile. Compiling before verifying records an unproven state as if it were an advance.
Report each iteration compactly:
ITERATION n: discovered <gap> → built <thing> → attack <c crit / h high> → patched <delta> → confidence <score>
Stop condition (all must hold)
Run ratchet score confidence and read BOTH loopClear and the workflow-closure layer
(closure.closed). Stop only when:
loopClearholds — no unresolved critical/high defect, no untested core assumption, no missing next action.workflowClosed.closedis true — the active artifact carries a closure certificate and no open defect is unattached.- The artifact is genuinely usable (passes its 5-point test).
If either read is false, run another iteration. Do not stop because the output "looks good" — the CLI reads are the arbiter, not your impression.
There is no convergence escape. If two iterations find nothing new while
workflowClosed.closed is false, you are not converged — you are blocked. Stop with
STOP REASON: blocked-needs-human, name the blocker the closure read printed, and hand it
over. "Nothing left to try" and "finished" are different states, and only one of them is
an ending.
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.
- 1mo ago First seen · 75 lines · 76 tokens per session scan A b47974f877cc
loop is a skill published in the GitHub repository Megaprompting/torque-loop (9 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 748 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
ulw-qa
This is an OMH ultraqa workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
evidence-audit
Evidence-led audit/fix rounds for any codebase in any language. Finds only defects that a runnable proof reproduces on current code, applies the narrowest in-scope patch, verifies with a second proof, promotes high-risk proofs to permanent regression tests, and reports exact validation results. Use whenever the user…
debugging
Use this skill when something is broken and the cause is unknown — a failing test, a crash, an error message, wrong output, a regression, a hang, or behaviour that differs between environments — and it has to be found and fixed at the root. Also use it to build the failing proof for a suspected defect before fixing…
test-iterate-loop
Autonomously diagnose a codebase, apply minimal fixes, and rerun tests until they pass or a real blocker is reached. Use when the user explicitly requests an iterative fix-until-green loop across Python, R, Julia, or HPC workflows.
refactor-ops
Safe refactoring patterns - extract, rename, restructure with test-driven methodology and dead code detection. Use for: refactor, refactoring, extract function, extract component, rename, move file, restructure, dead code, unused imports, code smell, duplicate code, long function, god object, feature envy, DRY…
pair-programming
AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switching, continuous code review, security scanning, and performance optimization with…