wixie

Deep research engine (E0) that produces a verified, cited claims artifact before prompts are engineered. Decomposes the query, fans out parallel Haiku fetchers, triangulates claims across independent sources, synthesizes, and verifies every claim traces to a fetched quote. Auto-fires inside /create when the topic depends on external or time-sensitive facts. Also callable standalone. Auto-triggers on: "/deep-research", "/research", "research this topic", "look up the current state of", "what's the latest on", "fact-check this", "find sources on", "before we craft the prompt, research". Do not use for static topics (pure logic, timeless writing tasks) or when a fresh brief already exists (freshness < 30 days) — reuse it. Do not use to render an existing brief — use /research-render for that.

Runs the Wixie model-freshness aggregator over state/model-usage.ndjson and flags any models-registry.json entry whose sunset_date has elapsed. Use when the developer asks about model deprecation, registry staleness, retired models, sunset dates, F-006 closure, or wants a current freshness summary. Auto-triggers on: "model freshness", "registry stale", "deprecated models", "sunset", "F-006", "freshness report", "model usage telemetry". Do not use for emitting telemetry events (the SessionStart hook does that automatically) or for editing the registry itself (developer edits the JSON directly).

Run the Convergence Engine on any prompt file. Iterates up to 100 times, automatically fixing clarity, completeness, efficiency, model fit, and failure resilience until the prompt reaches DEPLOY quality. Auto-triggers on: "/converge", "converge this prompt", "optimize until perfect", "iterate until deploy", "run convergence".

Creates optimized, model-fitted prompts from raw task descriptions with technique selection and explained reasoning. Auto-triggers on: "I need a prompt for", "build me a prompt", "make this prompt better", "optimize this prompt", "help me prompt", "write a system prompt", "what prompting technique should I use", "how should I structure this prompt", "/create".

Tests a prompt for security vulnerabilities — injection attacks, jailbreak patterns, data leakage risks. Reports exploits found and suggests specific defenses. Use on any user-facing or API-deployed prompt. Auto-triggers on: "/harden", "harden this prompt", "test for injection", "is this prompt safe", "security check prompt", "red team this prompt".

Improves existing prompts by re-selecting techniques, adapting format to the target model, and fixing weaknesses while preserving the user's intent and domain knowledge. Auto-triggers on: "make this prompt better", "improve this prompt", "refine this prompt", "fix this prompt", "optimize this prompt", "what's wrong with this prompt", "/refine".

Runs a prompt's test suite (tests.json) by executing each test case, checking output against expected_contains assertions, and reporting pass/fail results. Use for regression testing after refinements. Auto-triggers on: "/test-prompt", "test this prompt", "run prompt tests", "check if the prompt works", "regression test".

Converts a prompt from one model's format to another. Re-selects techniques, adapts structure, preserves intent and domain content. Auto-triggers on: "/translate-prompt", "convert this prompt to GPT", "adapt for Claude", "port this prompt to Gemini", "make this work on o3", "translate prompt".

Searches across existing research briefs for claims, sources, or contradictions matching a query. Read-only — returns matching claims with cites, does not regenerate or re-fetch. Use to check whether a topic has already been researched, to pull specific facts from a prior brief, or to cross-reference claims across multiple briefs. Auto-triggers on: "/research-query", "do we have research on X", "what did the brief on Y say about Z", "find claims about", "search the briefs for", "have we already looked into". Do not use to run new research — use /deep-research for that.

Audits freshness across all briefs. Lists briefs by age class — current (<30d), aging (30-90d), stale (>90d). Optionally re-runs stale briefs via /deep-research. Use for weekly or monthly maintenance, or before a big /create session where multiple topics will be referenced. Auto-triggers on: "/research-refresh", "check brief freshness", "which briefs are stale", "audit the research cache", "refresh stale briefs". Do not use for a specific topic — use /deep-research <topic> for that.

Renders claims.json into a human-readable report.md for an existing research brief. Pure transformation — no new research, no new verification. Use when a developer wants to review research without re-running the full loop, or when a brief needs to be presented as a readable document. Auto-triggers on: "/research-render", "render the brief", "show me the brief", "render the research report", "I want to read the brief on X", "make the brief readable". Do not use to modify claims, re-fetch sources, or re-verify — use /deep-research for that.

Render the top-of-context briefing for a target plugin. Reads the inference-engine catalog, filters elevated patterns tagged for the target plugin, writes state/briefings/<plugin>.md. Use before a session where the target plugin is about to do high-stakes work (e.g. /converge, /lich-review). Safe and cheap — rendering is a pure function of the current catalog. Auto-triggers on: "/inference-brief", "render the wixie briefing", "refresh briefings", "prep the ufopedia brief for <plugin>".

Append a single artifact (failure observation, correction, precedent) to the inference-engine's append-only stream. Use when a cross-session-relevant event occurs — a self-caught failure mode, a corrected misunderstanding, a precedent worth compounding. The emit is a no-op unless WIXIE_INFERENCE_ENABLED=1 is set. Auto-triggers on: "/inference-emit", "emit this to ufopedia", "log this as a precedent for future sessions", "record this failure pattern".

Search the inference-engine catalog. Accepts a code (F07, OP05, …), a tag (wixie, lifecycle, …), or a 16-char pattern_id. Returns the full pattern records as JSON. Read-only; cheap; safe to call ad-hoc. Auto-triggers on: "/inference-query", "what does F07 say", "show patterns tagged lifecycle", "search ufopedia for …".

Reconcile the inference-engine catalog. Re-fingerprints every artifact, re-runs Wald SPRT and Beta-Binomial and EMA decay, elevates patterns that cross the SPRT threshold, retires patterns that fall below it, and atomically rewrites catalog.json. Safe to run repeatedly — fully idempotent on identical artifact streams. Auto-triggers on: "/inference-reconcile", "rebuild the catalog", "re-elevate patterns", "refresh ufopedia", "reconcile learnings".

Internal reviewer agent. Validates a completed prompt folder against metadata.json and models registry. Checks consistency, completeness, and production-readiness. Not user-invocable — triggered automatically by the prompt-creator after convergence completes.