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/burnnpx skills add Megaprompting/torque-loop --skill burngit 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 | $0.00065 | $0.00497 |
| Opus 5 | $0.00032 | $0.00249 |
| Sonnet 5 | $0.00013 | $0.00099 |
| Haiku 4.5 | $0.00006 | $0.00050 |
Grade A, and why
burn 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:burn — option debt collection
Open options feel like freedom. They are actually a tax: every one you carry costs attention whether or not you act on it. This command collects the debt. It kills what is dead, parks what is premature, and keeps only what earns its place.
Step 0 — Load state
ratchet status
ratchet state get openLoops
Procedure
For each open option, possibility, or half-started thread:
- Why it's attractive — the real pull. Usually optionality, sunk cost, or ego.
- What fear keeps it alive — the thing you're afraid happens if you kill it. Name it; fears shrink when named.
- What gets simpler if it dies — the concrete relief. Fewer branches, clearer focus, less maintenance.
- Verdict:
- KILL — no path where this matters; end it.
- PARK — might matter later, not now; freeze it with a revisit trigger.
- KEEP — actively advancing the target; it stays.
Output contract
| Option | Attractive because | Fear keeping it alive | Simpler if killed | Verdict |
| ------ | ------------------ | --------------------- | ----------------- | ------- |
| ... | ... | ... | ... | KILL/PARK/KEEP |
BURN NOW: <the one option to kill this minute>
DECISION SENTENCE: "<exact words that end it>"
Serialize
Killed and parked options leave state as closed loops so they stop costing attention:
ratchet state append openLoops '{"text":"KILLED: <option>","status":"closed"}'
ratchet state append openLoops '{"text":"PARKED until <trigger>: <option>","status":"open"}'
ratchet state set phase decide
Next: /ratchet:decide on what remains, or /ratchet:build if only the keeper is left.
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 · 55 lines · 65 tokens per session scan A b33b3e7938a6
burn is a skill published in the GitHub repository Megaprompting/torque-loop (5 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 497 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.