kernel

Systematic debugging and refactor analysis. Diagnosis before prescription. Bug mode: reproduce, trace, isolate, hypothesize, diagnose. Refactor mode: map, trace deps, measure coupling, risks, diagnose.

Deep creative exploration engine. Competing perspectives, stress-tested by a 4-persona council, scored by integrity. The approach that survives attack wins — not the one that sounds best.

Autonomous development engine. Heats solutions with adversarial entropy, hammers them through iteration, quenches with quality gates. Runs until antifragile or reports why it can't be. Run overnight, come back to shipped code.

Generate context handoff brief for session continuation. Saves state, decisions, next steps. Triggers: handoff, save, pause, context, continue later.

Show KERNEL help. What commands do, how to use them, current plugin status. Triggers: help, how, what, commands.

Guided entry point. Research → classify → scope → execute. Human confirms each phase. Triggers: start, begin, do, implement, build, fix, create.

Initialize KERNEL globally. Sets up Vaults, symlinks, CLI, database.

Observability dashboard. Session stats, agent tracking, hook performance, learning health. Triggers: metrics, stats, dashboard, observability.

Cross-session learning synthesis. Finds patterns, resolves contradictions, promotes insights. Triggers: retrospective, reflect, patterns, learnings, synthesis.

Code review for PRs or staged changes. >80% confidence threshold. Verdict: APPROVE, REQUEST CHANGES, or COMMENT. Triggers: review, pr, code review.

Critical pre-implementation review. Find what AI breaks. Verdict: PROCEED, REVISE, or RETHINK. Triggers: review plan, tear apart, critique, analyze.

Pre-commit verification. Build, types, lint, tests, security scan. Blocks on failure. Triggers: validate, check, verify, pre-commit, ship.

QA - assume broken, find edge cases, prove with evidence

Cross-task intelligence. Detects dependencies, batches related work, spots systemic patterns.

Extracts patterns from human review decisions. Progressive rule promotion.

Whole-codebase reasoning with 1M context. Maps structure, dependencies, risk zones.

Structured post-mortem with telemetry evidence. Determines cause of death for failed work.

Multi-perspective debate agent. Generates minimalist, maximalist, and pragmatist approaches grounded in actual codebase context.

Composite orchestrator. Spawns parallel multi-lens validators before release.

Deep research agent. Finds existing solutions, evaluates packages, documents pitfalls before any implementation begins. Spawned by orchestrator when encountering unfamiliar tech, new integrations, or package selection decisions.

Code review agent. Reviews PRs and code changes for quality.

Codebase reconnaissance agent. Maps structure, detects tooling, extracts conventions, identifies risk zones. Spawned by orchestrator on first interaction with unfamiliar codebase or when discovery is needed.

Minimal diff implementation, commit every working state

Haiku-powered complexity classifier. Single fast call before expensive work.

Haiku pre-flight before expensive surgeon spawns. Validates approach viability cheaply.

Pre-commit validation agent. Runs types, lint, tests, and checks invariants before any code is committed or merged. Spawned by orchestrator during /kernel:validate or automatically before /kernel:ship.

REST API design patterns. Resource naming, status codes, pagination, error responses, versioning. Triggers: api, rest, endpoint, route, http, status-code, pagination.

Mobile/web app build pipeline, EAS, store submission, pre-submission checklists. Triggers: app, mobile, EAS, store submission, build, deploy app, expo, react native, flutter.

System architecture and design patterns. Modular design, interface stability, dependency management, AI-code health nexus. Triggers: architecture, design, structure, modules, dependencies, coupling, system design.

Backend architecture patterns. Repository pattern, caching, queues, N+1 prevention, transactions. Triggers: backend, server, database, cache, redis, queue, repository, service.

Solution exploration and implementation. Generate 2-3 approaches, pick simplest. Never implement first idea. Triggers: build, implement, create, feature, add.

Context engineering and token management. Compaction strategies, progressive disclosure, structured note-taking via AgentDB. Triggers: tokens, compaction, memory, handoff, summarize, context window.

Systematic debugging methodology based on Zeller's scientific method. Reproduce, hypothesize, predict, test, isolate via binary search, fix root cause. Every fix gets a regression test. Triggers: bug, error, fix, broken, not working, fails, crashed, unexpected, stack trace, regression, exception.

Frontend aesthetics and UI implementation. Break generic AI aesthetic patterns. Create distinctive, surprising interfaces. Supports mood variants that guide aesthetic direction without constraining execution. Triggers: design, frontend, ui, styling, css, visual, theme, component, layout, abyss, spatial, verdant, substrate, ember, arctic, void, patina, signal.

End-to-end testing with Playwright. Page Object Model, flaky test strategies, CI integration. Triggers: e2e, playwright, browser, end-to-end, integration-test, ui-test.

Eval-Driven Development (EDD) for AI workflows. pass@k metrics, capability evals, regression evals. Triggers: eval, edd, pass@k, capability, regression, benchmark.

Git workflow and version control best practices. Atomic commits, conventional messages, branch strategies, merge protocols. Triggers: commit, branch, merge, rebase, git, push, pull, PR, version control.

Multi-agent orchestration patterns. AgentDB as structured briefing, 4 fault tolerance layers (retry, fallback, classification, checkpointing), context transfer protocols. Triggers: orchestrate, coordinate, agents, parallel, spawn, contract, tier 2, tier 3.

Performance optimization and profiling. Measure before optimizing, identify bottlenecks, avoid premature optimization. Triggers: performance, speed, slow, optimize, latency, throughput, profiling, benchmark.

AI code quality checks. The Big 5: input validation, edge cases, error handling, duplication, complexity. Triggers: quality, big 5, ai code, review, validate.

Safe refactoring methodology. Behavior-preserving transformations only. Tests green before AND after. Triggers: refactor, clean, simplify, restructure, extract, inline.

Security best practices and vulnerability prevention. Input validation, authentication, secrets management, OWASP top 10. Triggers: security, auth, authentication, secrets, credentials, vulnerability, injection, XSS, CSRF, rate-limit.

Test-Driven Development workflow. Tests BEFORE code. Red-green-refactor cycle. Triggers: tdd, test-first, test-driven, red-green, coverage.

Testing methodology and strategy. Tests prove behavior, not implementation. Triggers: test, tests, coverage, assertion, mock, fixture, spec, verify.

13 hooks across 8 events