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/locknpx skills add Megaprompting/torque-loop --skill lockgit 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 | $0.00067 | $0.00743 |
| Opus 5 | $0.00034 | $0.00371 |
| Sonnet 5 | $0.00013 | $0.00149 |
| Haiku 4.5 | $0.00007 | $0.00074 |
Grade A, and why
lock 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ratchet:lock — scope lock
Ambiguity is where work goes to die. This command converts a wish into a target with edges. You do not begin work until the target is locked — but you also do not stall for missing information you can assume. Name the assumption and move.
Step 0 — Load state
ratchet status
Procedure
Interrogate the input until every field below has a concrete answer. Where the input is silent, infer the most reasonable value and mark it as an assumption.
- Literal object — the exact noun being operated on (this file, this prompt, this route, this dataset). Not a category. The specific thing.
- Operation — the single verb (build, fix, rank, migrate, decide, audit).
- Desired output shape — the concrete form of the result (a JSON file, a patch, a 3-row table, a 200-word spec). If you can't name the shape, the target isn't locked.
- Real outcome — what becomes true in the world when this is done. The reason, not the deliverable.
- Proof-of-done — the observable test that flips from fail to pass. One sentence, checkable by someone else.
- Smallest progress artifact — the tiniest thing you could produce in the next 20 minutes that is undeniably forward motion.
- Highest-information missing variable — the one unknown whose answer would change the plan most.
- Assumption if missing — the value you will adopt for that variable so work can start now, stated explicitly so it can be challenged later.
Output contract
OBJECT: <literal noun>
OPERATION: <single verb>
OUTPUT SHAPE: <concrete form>
REAL OUTCOME: <what becomes true>
PROOF-OF-DONE: <the checkable test>
SMALLEST ARTIFACT: <20-minute forward motion>
MISSING VARIABLE: <highest-information unknown>
WORKING ASSUMPTION: <adopted value + one-line justification>
Serialize
ratchet state set objective "<operation> <object> → <output shape>, proof: <proof-of-done>"
ratchet state set phase lock
Meter what follows
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 · 74 lines · 67 tokens per session scan A 286a97ca0af5
lock is a skill published in the GitHub repository Megaprompting/torque-loop (5 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 743 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.