kernel

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

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

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

Save bounded progress as kernel.checkpoint/v1 for exact resume after reset. Triggers: checkpoint, save progress, context reset, compact soon, long task.

Context engineering: compaction, progressive disclosure, structured notes via AgentDB. Triggers: tokens, compaction, memory, handoff, summarize, context window.

Diagnosis before prescription: reproduce, hypothesize, isolate, fix root cause, add a regression test; refactor mode maps deps, coupling and blast radius. Triggers: bug, error, fix, broken, not working, crashed, stack trace, exception, refactor, restructure, coupling, dependency map.

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.

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

Rules as hypotheses: falsifiable tests, confidence updates, graduate or kill. Triggers: experiment, hypothesis, prove, test rule, validate methodology, evidence.

Autonomous development with experimental self-correction. Iterates through quality gates until antifragile or blocked.

Context-led frontend design: art direction derived from product, audience, brand and the existing system, not generic defaults. Named mood variants listed inside. Triggers: frontend, UI, CSS, styling, visual, theme, component, layout, responsive, accessibility, animation.

Audit or explicitly synchronize Claude and Codex repository governance without overwriting conflicts. Triggers: governance sync, CLAUDE.md, AGENTS.md, instruction mirror.

Save provenance, decisions, phases, context policy, and next steps as kernel.handoff/v1. Triggers: handoff, save, pause, context, continue later.

Show KERNEL help. The unified skill system, state operations, agents, current plugin status. Triggers: help, how, what, skills, commands.

Guide real-build acceptance: literal taps, real inputs, expected outcomes, worst case first, one sitting. Triggers: testflight, human pass, acceptance test, before we ship, what should I test, release checklist, device test.

Entry point for new or resumed work. Researches and scopes new tasks; validates and resumes handoff/checkpoint manifests. Triggers: start, begin, do, implement, build, fix, create, resume, continue.

Initialize KERNEL links and AgentDB in a confirmed Vaults directory.

Build, refresh and query a deterministic code knowledge graph to cut orientation-token cost. Triggers: knowledge graph, graphify, code graph, god nodes, orientation cost, map the codebase, what connects, callers of, blast radius.

Explicit landing-page build and deploy operator. Loads marketing and frontend judgment, scaffolds the smallest suitable site, verifies it rendered, deploys to the configured target.

Honest marketing-site method: audience, offer, proof, objections, privacy, art direction, handoff. Triggers: marketing site, landing page, company website, portfolio, campaign page, conversion, positioning, value proposition, CTA, social proof, privacy policy.

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

Multi-agent orchestration: lane contracts, worker-model doctrine, fault tolerance. Triggers: orchestrate, coordinate, agents, parallel, spawn, contract, tier 2, tier 3.

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

Audit whether prior learnings actually fired, then install mechanisms for this run's recurrences. No finding without an install path and a firing test. Triggers: retrospective, reflect, what did we learn, patterns, post-mortem, why does this keep happening.

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

Release-gate sequence: validate → review → push → tag. Wraps kernel:git mechanics with the pre-ship safety chain. Triggers: ship, release, push to main, ready to merge, deploy.

Simplify code, plans and systems without losing required outcomes; delete machinery that earns nothing; for code, AST-measured complexity with regression gates. Triggers: simplify, refactor, complexity, overengineered, dead code, useless guard.

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