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 skills/megaprompting/torque-loop/cutnpx skills add Megaprompting/torque-loop --skill cutgit clone --depth 1 https://github.com/Megaprompting/torque-loopWhat 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 | $0.00062 | $0.00537 |
| Opus 5 | $0.00031 | $0.00269 |
| Sonnet 5 | $0.00012 | $0.00107 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
cut 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 2d 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.
What it actually says
/ratchet:cut — the anti-delusion pass
Every plan rests on assumptions. Most are fine. A few are load-bearing and wrong, and those are the ones that waste days. This command finds them and hands you the cheapest test to kill each before it costs you.
Step 0 — Load state
ratchet status
Procedure
-
Surface the assumptions the current objective and chosen bottleneck depend on. Include the silent ones — "the API returns what the docs say", "the user actually wants this", "this file is the source of truth", "the test suite covers this path".
-
For each assumption, specify:
- Breakage mode — what specifically goes wrong if it is false.
- Detection signal — the observable that would reveal the break.
- Falsification test — the cheapest action that would prove it false. Prefer a five-minute check over a five-hour build.
-
Rank by damage × likelihood. An assumption that is cheap to test and catastrophic if wrong goes first.
-
Pick the top three kill-tests — the ones worth running before any further build. A kill-test is a test designed to end the plan cheaply, not to confirm it.
Output contract
ASSUMPTIONS (ranked by damage × likelihood):
- <assumption> | breaks: <mode> | signal: <detection> | test: <cheapest falsification>
- ...
TOP 3 KILL-TESTS (run before building):
1. <test> — kills the plan if: <result>
2. ...
3. ...
Serialize
Record the riskiest untested assumptions so the loop can't forget them:
ratchet state append assumptions '{"text":"...","killTest":"...","status":"untested"}'
ratchet state set phase cut
Untested assumptions drain confidence (ratchet score confidence). Run the kill-tests,
then mark survivors: append with "status":"tested" or "status":"killed".
Next: if the plan survives, /ratchet:build. If a kill-test lands, /ratchet:lock again.
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.
- 2d ago First seen · 62 lines · 62 tokens per session scan A 110bbd117eae
cut is a skill published in the GitHub repository Megaprompting/torque-loop (5 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 537 once invoked, about $0.0003 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 skills, from other repositories
new-plugin
Factory line for adding a new HAR verification plugin (like playwright or rocketsim) for any framework — research the framework docs, build the template under src/templates/plugins/, register it everywhere, validate on a real repository, and open a PR. Use when asked to add/create a plugin, plugin template, or…
factory-line
Factory line for executing one station of a declared multi-station program — read the installed line bundle (har line status), plan parallel work into isolated HAR slots, run the cumulative gate with har line gate, and hand off for human review. Use when asked to "run a factory line", "run the next station", "execute…
v1-milestone
Factory line for executing one milestone of the HAR v1.0.0 refactor (epic os-factory/har#225) — plan the wave of parallel subagents, implement each issue in its own HAR slot, ship stacked PRs, run the fixture-e2e milestone gate, and hand off for review. Use when asked to "run the next v1 milestone", "work on v1.0.0"…
ctx
Codebase intelligence and evidence-driven governance with the indexed ctx CLI. Use when exploring an unfamiliar repository, locating symbols or callers, checking for existing implementations, estimating change impact, enforcing architecture rules, scoring a branch, finding hotspots or duplication, or analyzing…
ctx
Codebase intelligence and evidence-driven governance with the indexed ctx CLI. Use when exploring an unfamiliar repository, locating symbols or callers, checking for existing implementations, estimating change impact, enforcing architecture rules, scoring a branch, finding hotspots or duplication, or analyzing…
golden-rss
Use when testing the rss golden build.