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/decidenpx skills add Megaprompting/torque-loop --skill decidegit 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 | $0.00076 | $0.00556 |
| Opus 5 | $0.00038 | $0.00278 |
| Sonnet 5 | $0.00015 | $0.00111 |
| Haiku 4.5 | $0.00008 | $0.00056 |
Grade A, and why
decide 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 yesterday.
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:decide — the anti-menu
A menu of options is not a decision; it is deferred work. This command ends the menu. It returns one committed choice, defended, with a tripwire that says when to reverse it.
Step 0 — Load state
ratchet status
Procedure
-
Lay out the live options — only the ones genuinely on the table. Two to four. If there is only one, you don't need this command; if there are ten, cut first.
-
Score each on six axes (rate high/med/low, don't fake precision):
- Upside — how good the best case is.
- Reversibility — how cheaply you can undo it.
- Time-to-feedback — how fast reality tells you if it's working.
- Strategic compounding — whether it makes future moves easier.
- Cost of being wrong — the damage if it fails.
- Unlock value — what it makes possible that was blocked.
-
Choose one. State it as a decision, not a lean. Prefer reversible, fast-feedback options when scores are close — you learn faster and pay less for error.
-
Name the most tempting rejected option and why it loses. The one that was hardest to say no to. Give the single load-bearing reason it loses, not a list.
-
Set the reversal tripwire. The specific observable signal that means: this was wrong, reverse now. Without a tripwire, a bad decision runs forever.
Output contract
CHOSEN: <the decision, stated as committed>
FIRST ACTION: <the immediate move that commits to it>
REJECTED (most tempting): <option> — loses because <load-bearing reason>
REVERSAL TRIPWIRE: <observable signal → reverse>
Serialize
ratchet state append decisions '{"choice":"<chosen>","rejected":"<tempting rejected>","tripwire":"<reversal signal>"}'
ratchet state set phase build
Next: /ratchet:build the first action. A decision without a first action is still a menu.
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.
- yesterday First seen · 56 lines · 76 tokens per session scan A c4e8bcc382b4
decide is a skill published in the GitHub repository Megaprompting/torque-loop (5 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 556 once invoked, about $0.0004 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.