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/handoffnpx skills add Megaprompting/torque-loop --skill handoffgit 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 | $0.00072 | $0.00924 |
| Opus 5 | $0.00036 | $0.00462 |
| Sonnet 5 | $0.00014 | $0.00185 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
handoff 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.
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:handoff — transfer without loss
A handoff fails when the receiver has to reconstruct what you already knew. This command produces a self-contained brief that lets another model, agent, teammate, or future you start acting immediately — no re-reading the session, no re-deriving decisions.
Step 0 — Load state
ratchet receipt
ratchet export markdown
ratchet score confidence
Start from ratchet receipt — its eight fixed sections (target · delta · proof · seam ·
verdict · authority · state · next) are already the handoff spine; the steps below expand
each one for the receiver. Delegate to the ratchet-scribe subagent for a long or
high-stakes session.
Procedure
Compress the session to exactly what the receiver needs to act — and nothing they'd have to skim past:
- Objective — the locked target, one line.
- State of play — what's done, what's in flight, current confidence.
- Decisions made — commitments + their reversal tripwires (so the receiver doesn't relitigate settled calls).
- Artifacts — what exists, where, and each one's known holes.
- Open defects / risks — by severity.
- The single next action — the exact first move, concrete enough to start on.
- Context to act — the minimum files, commands, or facts the receiver needs. Point to locations; don't paste the world.
- Watch-outs — the traps you already hit or foresee.
- Deviations from the map — if
/ratchet:mapran, where the build diverged from its plan (map said X → code revealed Y → call made) and which calls still need the user's judgment. This is what stops the receiver from re-litigating what you already discovered. - Probe outcomes — for each probe: the unknown it attacked, the finding, and whether its code was disposed or explicitly promoted. An undisposed probe is a watch-out, not an asset — the receiver must not mistake build-for-learn residue for kept work.
Rules
- Self-contained. If the receiver needs to ask you a question to start, the handoff failed. Anticipate the first question and answer it.
- Compressed, not lossy. Cut commentary; keep every fact that changes a move.
- One next action, not a menu. Handoffs die in ambiguity — name the single move.
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 · 86 lines · 72 tokens per session scan A 1fe68265303b
handoff is a skill published in the GitHub repository Megaprompting/torque-loop (5 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 924 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.