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/mechanismnpx skills add Megaprompting/torque-loop --skill mechanismgit 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 | $0.00066 | $0.00484 |
| Opus 5 | $0.00033 | $0.00242 |
| Sonnet 5 | $0.00013 | $0.00097 |
| Haiku 4.5 | $0.00007 | $0.00048 |
Grade A, and why
mechanism 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:mechanism — the mechanism knife
Confusion is usually surface noise hiding a single mechanism. This command finds it. It does not produce a taxonomy of possible causes; it names the one causal handle you can actually pull.
Step 0 — Load state
ratchet status
Procedure
Given the confusing situation, separate cleanly — do not blur the layers:
- Surface symptoms — what you observe. The complaints, the errors, the friction.
- Underlying mechanism — the single process producing those symptoms. One precise model, not a list of possibilities.
- The constraint causing the mechanism — the limit or rule that forces this behavior.
- The feedback loop keeping it alive — why it persists instead of self-correcting.
- Highest-leverage intervention point — where a small push changes the most.
- The action that changes the mechanism — a move that alters the system, not one that merely re-describes it.
Rules
- Use one precise causal model. Resist the urge to enumerate five frameworks.
- Do not over-explain. The output is a handle, not an essay.
- Make the next move obvious — a mechanism you can't act on isn't named yet.
Output contract
SYMPTOMS: <what shows on the surface>
MECHANISM: <the one process underneath>
CONSTRAINT: <what forces it>
FEEDBACK LOOP: <what keeps it alive>
LEVERAGE POINT: <where to push>
CHANGING MOVE: <the action that alters the mechanism>
Serialize
If the mechanism reframes the objective or reveals the true bottleneck, update state:
ratchet state set bottleneck "<mechanism-level blocker>"
ratchet state set phase cut
Next: /ratchet:cut to test the mechanism's assumptions, or /ratchet:build the changing
move directly.
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 · 59 lines · 66 tokens per session scan A e88d105a6b23
mechanism is a skill published in the GitHub repository Megaprompting/torque-loop (5 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 484 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.