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/compilenpx skills add Megaprompting/torque-loop --skill compilegit 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 | $0.00074 | $0.00856 |
| Opus 5 | $0.00037 | $0.00428 |
| Sonnet 5 | $0.00015 | $0.00171 |
| Haiku 4.5 | $0.00007 | $0.00086 |
Grade A, and why
compile 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ratchet:compile — the state compiler
A session that isn't compiled evaporates. This command writes the breadcrumb: the compact record that lets the next agent — or you after a context reset — resume without re-deriving anything. Persistence has compression discipline: only what changes future behavior survives.
Step 0 — Load current state
ratchet status --json
Extend the existing record; do not overwrite it. For a heavy session, delegate to the
ratchet-scribe subagent.
What to serialize (and nothing else)
Save only: decisions, artifacts, defects, open loops, next action, next prompt. Delete interesting-but-nonoperative commentary. If it won't change a future move, it doesn't go in.
- Working title — a handle you'd recognize in a list of sessions.
- Current objective — the locked target, one line.
- Decisions made — actual commitments, with the rejected tempting option and tripwire.
- Artifacts created — title, kind, status, path, known holes.
- Defects / risks found — severity + summary + status.
- Open loops — what's unfinished and what would close it.
- Next action — the single immediate move.
- Next prompt/command — the exact
/ratchet:...to run next. - Retrieval tags — comma-separated handles for future search.
- One-sentence memory — the single line worth saving. Make it load-bearing.
Serialize (write it all through the CLI)
ratchet state set title "<working title>"
ratchet state set nextAction "<single next move>"
ratchet state set nextCommand "/ratchet:<command>"
ratchet state append decisions '{"choice":"...","rejected":"...","tripwire":"..."}' # if any new
ratchet artifact add '{"title":"...","kind":"...","status":"...","holes":["..."]}' # if any new
ratchet defect add '{"severity":"...","summary":"...","artifact":"<id>"}' # if any new
ratchet state append openLoops '{"text":"..."}' # if any
ratchet state set phase compile
ratchet compile done
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 · 86 lines · 74 tokens per session scan A c8736dd18213
compile is a skill published in the GitHub repository Megaprompting/torque-loop (5 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 856 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.