Megaprompting

Megaprompting/torque-loop

Plugin Claude Code

Plugin marketplace listing 1 plugin: ratchet.

Megaprompting/torque-loop

Plugin Claude Code

Torque Loop turns ambiguous work into shipped artifacts through target locking, adversarial validation, patching, and state serialization — plus a bounded /ratchet:evolve loop. A stateful advancement engine, not a prompt library. Not affiliated with Anthropic.

Megaprompting/torque-loop

Skill Claude CodeCodex

The pre-PR hostile pass for torque-loop. Runs scripts/preflight.js for the deterministic checks (tests, version alignment, dependency gate, leak scan, trace tags) then applies human judgment to the checks a script can't rule on (testless changes, prose-enforcement, diff minimality, parked-decision creep, scope…

Megaprompting/torque-loop

Skill Claude CodeCodex

Cut a Torque Loop release end-to-end and stop at the PR — branch, bump all five version fields, promote the CHANGELOG with lineage + slogan, verify with npm test + doctor, commit chore(release). Use when [Unreleased] has earned a version. Never merges, tags, or publishes a Release; those are Danny's.

Megaprompting/torque-loop

Skill Claude CodeCodex

Add or evolve a /ratchet: command across every synced surface at once — canonical prompt in PROMPTS.md, SKILL.md in the house shape, README row, templates, drift guard, tests. Use when a new loop move is being added to the plugin (like map or the probe were), or an existing skill's contract is changing. Prevents the…

Megaprompting/torque-loop

Instructions file

Instructions for Megaprompting/torque-loop: You are the continuation maintainer of Torque Loop, resuming it in a fresh context. Torque Loop is a zero-dependency Claude Code + Codex plugin (Node ≥ 18, CommonJS, no build step) that turns ambiguous work into shipped, tested, serialized artifacts through evidence-gated…

Megaprompting/torque-loop

Agent

Attacks artifacts, assumptions, and self-serving reasoning. Use to run hostile validation on anything that looks finished. Produces concrete failure modes with severity and the smallest patch each demands — never praise, never "looks good".

Megaprompting/torque-loop

Agent

Produces the smallest usable artifact for a locked target. Use when a target is defined and something concrete must exist — a spec, prompt, checklist, patch, test plan, or decision record. Refuses to discuss; it ships a v0 with explicit holes and a working test.

Megaprompting/torque-loop

Agent

Serializes session state, decisions, defects, and next moves into durable Ratchet state. Use to compile a session into a breadcrumb the next session can resume from cold. Writes state via the ratchet CLI; never invents facts not present in the session.

Megaprompting/torque-loop

Hook

Runs when a session starts, running an inline shell check. From Megaprompting/torque-loop.

Megaprompting/torque-loop

Hook

Runs after a tool call finishes for Write, Edit, MultiEdit and NotebookEdit tool calls, running an inline shell check. From Megaprompting/torque-loop.

Megaprompting/torque-loop

Hook

Runs when the agent finishes a response, running an inline shell check. From Megaprompting/torque-loop.

Megaprompting/torque-loop

Skill Claude CodeCodex

Run adversarial review on a finished-looking artifact. Use to replace self-praise with hostile pressure before shipping. Convenes a five-voice review board (impatient user, competitor, maintainer, auditor, saboteur), returns concrete failure modes with severity and evidence demanded, and the smallest patch each…

Megaprompting/torque-loop

Skill Claude CodeCodex

Rank the real blockers by leverage and pick the one bottleneck to attack. Use when there are many possible next moves and you risk doing interesting-but-not-advancing work. Scores obstacles by Leverage × Certainty × Speed-to-unblock × Risk-of-ignoring and names the winner and why it beats the tempting alternative.

Megaprompting/torque-loop

Skill Claude CodeCodex

Kill or park the options that are quietly draining energy. Use when you are carrying option debt — too many open possibilities, none advancing. Returns a kill / park / keep table, why each option is attractive, what fear keeps it alive, what gets simpler if it dies, and one option to burn right now.

Megaprompting/torque-loop

Skill Claude CodeCodex

Serialize the current session into durable state — the breadcrumb the next session resumes from. Use at the end of a work session or after any real advance. Returns working title, objective, decisions, artifacts, defects/risks, open loops, next action, next command, retrieval tags, and a one-sentence memory. Only…

Megaprompting/torque-loop

Skill Claude CodeCodex

Attack the hidden assumptions that could make the current plan look stupid in hindsight. Use before committing effort to a direction. Returns the load-bearing assumptions, how each breaks, the signal that would reveal the break, and the cheapest test to falsify it — then the top three kill-tests to run now.

Megaprompting/torque-loop

Skill Claude CodeCodex

Force a single defended choice instead of a menu of options. Use when analysis has produced alternatives but no commitment. Scores options on upside, reversibility, time-to-feedback, strategic compounding, cost-of-being-wrong, and unlock value; returns the chosen path, the most tempting rejected path and why it loses…

Megaprompting/torque-loop

Skill Claude CodeCodex

Evolve one artifact through a bounded, evidence-gated mutation loop — lock target, snapshot baseline, apply one pressure, generate candidate deltas, judge, patch, verify, keep or revert, record state, and name the next edge. Not brainstorming and not a general 'make this better': every kept change must be proven. Use…

Megaprompting/torque-loop

Skill Claude CodeCodex

Produce a compact handoff for another model, agent, teammate, or future session. Use when work must transfer without losing state. Returns a self-contained brief — objective, what's done, what's decided, what's open, the exact next action, and the context needed to act — compressed so the receiver can start…

Megaprompting/torque-loop

Skill Claude CodeCodex

Run the full consequence loop on any messy task, project state, prompt pile, codebase goal, or vague direction. Use this when you do not know which Ratchet command to use. Locks a target, ranks blockers, cuts assumptions, builds the smallest artifact, attacks it, patches failures, and serializes state — ending with…

Megaprompting/torque-loop

Skill Claude CodeCodex

Convert vague input into a locked, executable target. Use when a task is fuzzy, over-broad, or stated as a wish. Returns the literal object, operation, output shape, real outcome, proof-of-done, smallest progress artifact, the highest-information missing variable, and the assumption to adopt if it stays missing.

Megaprompting/torque-loop

Skill Claude CodeCodex

Run recursive improvement — build → attack → patch → compile — until the artifact is genuinely done. Use to drive an artifact to a stable, tested, serialized state without stopping at the first draft. Repeats the cycle and reports an iteration log and confidence score, stopping only when no critical/high defect, no…

Megaprompting/torque-loop

Skill Claude CodeCodex

Map the fog before you build. Use when uncertainty is high (aperture A3–A4), the terrain is unfamiliar, the taste is "I'll know it when I see it", or you are porting a reference implementation. Walks the task through four unknown-quadrants — known knowns (settled ground with file evidence), known unknowns (one…