/autoresearch

name: autoresearch
description: "Autonomous goal-directed iteration loop: modify, verify, keep/discard against a metric or a checkable success predicate, with bounded cycles, plateau/ceiling backstops, safety-screened commands, and a ship gate that never auto-approves. Use for iterate-and-verify improvement loops, multi-bug zeroing, security hardening loops, and regression-gated shipping. Not for one-shot questions, single-bug diagnosis without a loop (spec-debug), ordinary code review (spec-code-review), implementation planning (spec-plan), or goals whose success cannot be expressed as a checkable signal — name the destination skill and route out."

Autoresearch — Autonomous Goal-directed Iteration

Safety Invariants (all subcommands)

• Never push, publish, or deploy without explicit user approval.
• Bounded by default. Override with `Iterations: unlimited`.
• All results logged to `autoresearch/{subcommand}-{YYMMDD}-{HHMM}/` directory.
• Chain handoff via `handoff.json`. Evals reads `*-results.tsv`.

Dispatch (bare `autoresearch`)

Parse the invocation in this order:

| Condition | Mode | |---|---| | `Metric:` or `Verify:` present | **Classic** — existing metric loop, unchanged | | Free-form natural-language goal, no metric/verify | **Orchestrator** — see Orchestrator section | | Nothing | **Setup wizard** — interactive config builder | | `--classic` flag | Force Classic regardless of goal text | | `--auto` flag | Force Orchestrator regardless of goal text |

**Mode banner gate.** Resolve the mode from the table below, then emit `[autoresearch] mode: <classic|orchestrator|wizard>` as your next assistant message once the skill definition is loaded — before any work tool call (test runs, file edits, project scaffolding) or planning output. No work may start before the banner is emitted; a run that starts working without it is a dispatch violation even if the work itself is correct. If the mode cannot be resolved, emit `[autoresearch] mode: unresolved` and ask exactly one clarifying question.

Subcommands

| Command | Does | Default Iterations | |---|---|---| | `autoresearch` | Iterate against a metric: modify → verify → keep/discard | 25 | | `autoresearch plan` | Convert a goal into validated Scope, Metric, Verify config | N/A | | `autoresearch debug` | Hunt bugs: hypothesize → test → falsify → repeat | 15 | | `autoresearch fix` | Crush errors one-by-one until zero remain | 20 | | `autoresearch security` | STRIDE + OWASP audit with red-team personas | 15 | | `autoresearch ship` | Ship through 8 phases: checklist → dry-run → deploy → verify | N/A | | `autoresearch scenario` | Generate edge cases across 12 dimensions | 20 | | `autoresearch predict` | 5 expert personas debate before implementation | N/A | | `autoresearch learn` | Scout codebase → generate docs or wiki → validate → fix loop | 10 | | `autoresearch reason` | Adversarial debate with blind judges until convergence | 8 | | `autoresearch probe` | 8 personas interrogate requirements until saturation | 15 | | `autoresearch improve` | Research ICP challenges, discover improvements, generate PRDs | 15 | | `autoresearch evals` | Analyze iteration results: trends, plateaus, regressions | N/A | | `autoresearch regression` | Regression stability gate: baseline vs candidate, verdict STABLE/UNSTABLE | N/A |

Universal Flags

| Flag | Applies To | Purpose | |---|---|---| | `Iterations: N` | All looping | Set iteration count | | `Iterations: unlimited` | All looping | Opt-in unbounded | | `--evals` | All looping | Mid-loop checkpoints + final summary | | `--evals-interval N` | All looping | Override checkpoint frequency | | `--chain <targets>` | All | Sequential handoff after completion | | `--<subcommand>` | All | Shorthand for `--chain <subcommand>` | | `--dry-run` | Orchestrator | Print derived config + planned pipeline; no execution | | `--max-cycles N` | Orchestrator | Hard ceiling on orchestration cycles (default 50) | | `--classic` | Bare `autoresearch` | Force Classic metric-loop mode | | `--auto` | Bare `autoresearch` | Force Orchestrator mode |

Orchestrator

Activated when a plain-language goal is given without `Metric:`/`Verify:`. Classifies the goal into a **Goal archetype** — see `references/orchestrator-routing.md` for the archetype table and router decision table.

**Two modes based on archetype:**

• **Orchestration loop** — predicate-bearing archetypes (ship-ready, optimize-metric, fix-broken, harden, build-feature, explore). Goal has a mechanical Success predicate; the loop runs until that predicate is met.
• **Single-pass dispatch** — subjective/terminal archetypes (document, what-to-build, decide-design). Routes once to the fitting subcommand (learn / improve / reason), lets it self-terminate, then reports. No loop, no Plateau, no ship gate.

Orchestration Loop Steps

Backed by `scripts/orchestrate.sh` (deterministic seam — all routing logic lives there). Subcommands exposed: `classify`, `next-hop`, `units`, `plateau`, `screen-cmd`, `verdict`, `validate-state`, `screen-state-predicate`.

1. **Classify** — `scripts/orchestrate.sh classify "<goal>"` → archetype label + mode. 2. **Derive predicate** — reuse `plan` logic to produce a concrete Success predicate: exact shell command + expected output. For `optimize-metric`, run the full plan/wizard derivation internally. 3. **Confirm** — ONE `request_user_input` showing: archetype, mode, concrete predicate (command + expected output), terminal choice (stop-at-verified vs proceed-to-ship). Misclassifications are caught here, not mid-run. 4. **Round-0 dry-run** — prove the predicate command runs and returns a value; safety-screen every derived command via `screen-cmd`; print projected cycle budget. Stop here if `--dry-run`. 5. **Loop** until predicate satisfied: a. Assess state via cheap signals (last `handoff.json`, regression verdict, error count) + affected-test verify. b. `scripts/orchestrate.sh next-hop orchestrator-state.json` → next subcom