JASON-OS

Dual-lens repo analysis: Creator View (knowledge, insights, home-repo comparison) + Engineer View (health, security, process). Two user-invokable depths (Standard / Deep); Quick Scan is triage-only. Link mining for curated lists. Fit separation via dual scoring lenses. Outputs to .research/analysis/<repo-slug>/.

Structured discovery-first planning for complex tasks. Ask exhaustive categorized questions, build a standalone decision record, then produce a step-by-step implementation plan with audit checkpoints and convergence-loop verification of diagnosis and plan claims for user approval before any code is written.

Interactive behavioral quality audit for individual skills. Evaluates against 12 quality categories (including T25 convergence loop and completion verification) to surface attention management issues and produce actionable decisions. Includes self-audit verification that all decisions were actually implemented. Uses convergence loops in its own discovery phase. Produces a decision record and updated skill files.

Structured workflow for creating or updating skills — from discovery through validation and audit. Produces structurally correct, behaviorally effective skill packages (SKILL.md + companions) using deep-plan-style discovery with skill-specific question categories and convergence-loop verification of codebase claims.

Audit + refresh the JASON-OS / SoNash label catalogs. Dispatches primary + secondary derivation agents in byte-weighted batches, cross-checks their output, and presents drift / low-confidence / disagreement findings for conversational resolution (D12a). Supplementary skill per D4 + D19 — catalogs remain correct via the PostToolUse hook (§S3) + pre-commit validator (§S6) even if this skill is never invoked.

Multi-agent research engine that decomposes questions, dispatches parallel searcher agents, synthesizes findings with citations and confidence levels, runs mandatory contrarian/OTB challenges, gap-pursuit verification, and cross-model verification via Gemini CLI, and produces structured output with downstream adapters, research index, and management commands.

Session closure pipeline — context preservation, optional compliance review, and final commit. Ensures the next session starts with accurate context. v0: Foundation-scoped; Phase 3 metrics pipeline and most Phase 2 compliance steps are gated on Layer 2 hooks landing.

Pre-flight checklist for work sessions — loads context, checks hook state, surfaces warnings, and gates on acknowledgment before work begins.

Process external PR code review feedback (Qodo, SonarCloud) through a structured 8-step protocol. Parses all items, categorizes by severity and origin, fixes in priority order, tracks deferred items via /add-debt, and captures learnings. This skill processes review feedback — it does not generate reviews.

Diagnose and fix pre-commit hook failures with user confirmation at each step. Reads hook output, classifies failures by category, spawns targeted subagents for complex fixes, and presents a structured report before re-committing. Reduces context waste from manual fix-commit-retry cycles. JASON-OS v0: Foundation-scoped to the gitleaks-only `.husky/pre-commit` scaffold; generic recipes (ESLint, Prettier, tsc, lint-staged) stay armed for when their triggers earn their place in the hook.

Log a technical-debt item to .planning/DEBT_LOG.md as a markdown table row. v0 stub — preserves /deep-research Phase 5 routing signal while a full debt system remains deferred.

Creative discovery phase for exploring ideas, directions, and design space before implementation planning or research. Uses Socratic dialogue, research-grade agents, and contrarian challenge to move from seed ideas to chosen directions with structured BRAINSTORM.md output that feeds directly into /deep-plan or /deep-research.

Save session state for recovery after compaction or failures. Default: save to local files (.claude/state/). With --mcp: also save to MCP memory for cross-session persistence.

Multi-pass verification of claims about reality using agent-based discovery, T20 tallies, and composable behaviors. Use when claims could waste effort if wrong — audits, discovery, doc-sync, plan verification.

Cross-session todo management with interactive menu, JSONL-backed persistence, and AI-powered context capture. Manages ideas, tasks, and insights that emerge during sessions so they survive across sessions. Independent of GSD.