GuitarAlchemist

Use when a pull request needs review by a different AI model than the one that authored it, or when configuring cross-model code review pipelines in CI/CD.

Run Demerzel's autonomous driver — full cycle or individual phases across all repos

Capture meaningful session state (current cursor, in-flight work, live hypotheses, open questions, do-NOT-carry-forward, success criteria) to state/digests/latest.md so the next session — including one after auto-compaction — can re-enter without re-discovering context cold. Distinct from /learnings (which captures surprises). Validates against docs/contracts/digest-schema.json.

Autonomous research scheduler — selects the most under-researched department by coverage ratio, generates questions from completeness gaps, cross-model validates, auto-produces courses at T>=0.8, rate-limited to 6 cycles/day with kill switch

Personalized AI tutor — turns any topic into a customized, progress-tracked learning course. Use when the user wants to LEARN a concept, skill, language, tool, or domain. Creates a MISSION, curated RESOURCES, iterative lessons with self-checks, and learning-records that persist across sessions. NOT for interrogating the user about their own design (use brainstorming/IDSD for that).

Run one bounded supervised autonomous cycle on the Demerzel governance repo. Picks the smallest unchecked governance slice inside allow_edit, implements it, runs the oracle (`pwsh scripts/verify.ps1`), emits cycle evidence, and stops. Refuses to run unless dev-process-overseer reports loop-eligible and the preflight passes. Use when asked to "run one supervised loop", "advance governance autonomously", or "do one cycle and stop".

Pause every /auto-optimize loop across the GuitarAlchemist ecosystem (GA, ix, Demerzel, tars) by writing the cross-repo HALT-ALL marker per the contract in ga/docs/contracts/2026-05-16-overseer-halt-marker.contract.md. Use halt/resume/status subcommands. Implementation is scripts/demerzel_halt.py.

Self-improvement reflex. When the user corrects an approach ("no, don't do that", "we discussed this before", "stop X"), captures the lesson as a permanent project rule appended to CLAUDE.md so the pattern doesn't repeat in this or future sessions. Cherny called this "the most important loop" in his 2026 Sequoia talk.

Test model robustness with adversarial attacks and defenses

Multi-armed bandit simulation — epsilon-greedy, UCB1, Thompson sampling

Benchmark and compare ix algorithm performance

Embedded Redis-like cache with TTL, LRU, pub/sub, and RESP protocol

Category theory primitives — monad laws verification, free-forgetful adjunction

Chaos theory analysis — Lyapunov exponents, bifurcation, attractors, fractals

Cluster data using K-Means or DBSCAN

Run ix real-world demo scenarios with optional multi-AI commentary via Octopus. Chains multiple ix MCP tools through curated narratives — chaos detection, governance, FinOps, sprint prediction.

Post-merge intent-vs-delivery evaluator. Resolves the most recent squash-merged PR, captures its stated intent (title + Summary), diffs it against what actually landed, runs /octo:review for specialist commentary, scans Codex bot comments (P0/P1 degrade the grade), computes a high/medium/low alignment score, and writes a structured grade to state/quality/pr-grades/<merge-sha>.json. Closes the "agent declared done, nobody checked the goal" loop.

Run one bounded supervised autonomous cycle on the Guitar Alchemist repo. Picks the smallest unchecked roadmap slice inside allow_edit, implements it, runs the oracle, emits cycle evidence, and stops. Refuses to run unless dev-process-overseer reports loop-eligible and the preflight passes. Use when asked to "run one supervised loop", "advance the roadmap autonomously", or "do one cycle and stop".

Rebuild the OPTIC-K voicing index (state/voicings/optick.index). Invoke when schema hash bumps, tag enrichment changes, new chord qualities are added, or the leak-test / invariant-coverage tools flag regressions. Mandatory precondition: stop any process that has the index mmap-locked — GaApi and GaMcpServer both hold the file open at runtime, and the write step WILL fail with IOException otherwise.

Generalized Cherny-style autonomous improvement loop. Reads a domain-scoped baseline.json + oracle script, runs the oracle, picks the worst-scoring item, proposes a fix, validates rollback safety, commits if metric improved AND roundtrip passes. Use for chatbot-qa, embeddings, voicing-analysis, or any other domain that has a baseline + oracle. Refuses to run if killswitch present, governance halt active, or scope_boundary violated.

End-to-end autonomous (AFK) harness that develops AND QAs the GA chatbot. Orchestrates the existing Level-3 /auto-optimize dev loop + the semantic /ga-chatbot-qa-panel judge workflow, instruments every step to a dashboard the human can watch, and enforces branch-only / never-merge safety. Use to run unattended chatbot-quality improvement with full human visibility. Refuses to run if the backend is down, a killswitch/halt marker is present, or scope_boundary is violated.

Turns raw Sentrux structural-quality metrics (quality_signal, cycle count, coverage) into a ranked list of actionable refactor recommendations with starter sketches. Pulls live data from sentrux MCP tools, optionally cross-references AI annotations (@ai:business-value, @ai:smell) and the latest /test-plan output, then writes 5-10 prescriptive bullets to state/quality/sentrux-next-steps/<date-Z>.md so the Sentrux dashboard tab can render them. PROPOSES — never auto-refactors; the human picks which recommendation to take.

Lists the seven diatonic triads of a key (root + major/minor). Calls the deterministic `domain.diatonicChords` closure via the `ga_dsl_eval` MCP tool — never recall diatonic sets from training data, since LLMs commonly mis-spell the iv/vii° in less-common keys (Gb major, F# minor).

Backlog grooming. Reads BACKLOG.md (H2 epics → H3 sub-sections), recent open GitHub issues, state/quality/ trend snapshots, state/digests/latest.md, and stale docs/plans/, then proposes a ranked top-3 work items with rationale. Writes the same content to state/backlog-grooming/<date>.md so the proposal survives session compaction. Closes the "agent picks whatever's loudest" failure mode in autonomous mode. PROPOSES — never auto-executes; the human approves.

Run a supervised autonomous loop on tars under explicit edit-scope and review-independence guardrails. Each cycle: preflight, propose, verify, halt-or-continue. Author and reviewer roles stay separate (producer-reviewer); the evaluator runs in a fresh sub-agent / fresh session and cannot self-certify. Contested cycles escalate to cross-vendor / multi-LLM review (Demerzel tribunal). Edits respect a line budget (rewrite-budget) so each diff stays small.

Self-improvement reflex. When the user corrects an approach ("no, don't do that", "we discussed this before", "stop X"), captures the lesson as a permanent project rule appended to CLAUDE.md so the pattern doesn't repeat in this or future sessions. Cherny called this "the most important loop" in his 2026 talk.

Capture meaningful session state (current cursor, in-flight work, live hypotheses, open questions, do-NOT-carry-forward, success criteria) to state/digests/latest.md so the next session — including one after auto-compaction — can re-enter without re-discovering context cold. Distinct from /learnings (which captures surprises). Validates against docs/contracts/digest-schema.json.

Diagnose GuitarAlchemist AFK routing, Claude Code, Jules, Agent Blackbox, submodule, and post-merge smoke failures before editing workflows.