rune-kit/rune
57 subagents
Subagent
adversaryPre-implementation red-team analysis. Challenges plans BEFORE code is written — edge cases, security holes, scalability bottlenecks, error propagation. Catches flaws at plan time (10x cheaper).architectArchitecture and planning agent. Spawned by plan, brainstorm, team, autopsy for strategic analysis, system design, and trade-off evaluation.asset-creatorCreates code-based visual assets — SVG icons, OG image HTML, social banners, icon sets. Code-only output (not raster PNG/JPG). Use browser-pilot + screenshot for raster.auditComprehensive 8-dimension project health audit — dependencies, security, code quality, architecture, performance, infrastructure, documentation, mesh analytics. Produces AUDIT-REPORT.md.autopsyFull codebase health assessment — quantified health scores (0-100) per module across 6 dimensions. Identifies highest tech debt. Use for rescue RECON or project diagnosis.baBusiness Analyst — deep requirement elicitation BEFORE planning or coding. Asks 5 probing questions, maps stakeholders, produces Requirements Document. Use when task is non-trivial or vague.brainstormCreative ideation — generates 2-3 approaches with trade-offs. Use when multiple valid paths exist or current approach has failed. Hands off to plan.browser-pilotPlaywright browser automation — navigate URLs, screenshot, interact with UI, check accessibility, capture console errors. Max 20 interactions. MUST close browser when done.coderCode writing and editing agent. Spawned by fix, test, surgeon when they need to write actual code. Follows parent skill instructions precisely.completion-gateLie detector for agent claims — validates every completion claim has actual evidence. Default-FAIL mindset. Use as final gate before merge/commit.constraint-checkInternal affairs auditor — checks whether HARD-GATEs and constraints were actually followed during workflow. Uses tool call ordering, not agent self-report.context-engineContext window management — tracks tool call count, auto-detects when context fills up, triggers state save + compaction. Artifact folding for large outputs (>4000 chars → file + preview).context-packCreates structured handoff briefings between agents. Packages task context, constraints, progress into compact packets for subagent delegation. Prevents 'lost context' in multi-agent workflows.cookFeature implementation orchestrator — handles 70% of requests. Full TDD cycle: understand → plan → test → implement → verify → commit. Use for ANY code modification (features, bugs, refactors,…dbDatabase workflow specialist — migration generation (up + down), breaking change detection, index recommendations, SQL injection scanning. Use when schema changes detected.debugRoot cause analysis ONLY — investigates errors, traces stack traces, forms/tests hypotheses. Does NOT fix code. Hands diagnosis to fix. Use when root cause is unknown.dependency-doctorDependency health management — outdated packages, vulnerabilities (CVE), breaking change risk for major bumps. Health score 0-100. Prioritized update plan: CRITICAL → SECURITY → PATCH → MINOR → MAJOR.deployDeploy to target platform — Vercel, Netlify, Fly.io, AWS, VPS. Pre-deploy verification + security gates. Tests and sentinel MUST pass first.designDesign system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.doc-processorGenerate and parse office documents — PDF, DOCX, XLSX, PPTX, CSV. Pure format utility for creating reports, exporting data, processing uploaded documents.docsAuto-generate and maintain project documentation — README, API docs, architecture docs, changelogs. Keeps docs in sync with code. The 'docs are never outdated' skill.docs-seekerDocumentation lookup — API signatures, examples, deprecation status. Priority: Context7 → llms.txt → WebSearch. Use for API reference, not general research.fixApply code changes from diagnosis or review findings. Locate → change → verify → report. Does NOT investigate — that's debug's job. Use after debug diagnosis or review findings.gitSpecialized git operations — semantic commits, PR descriptions, branch naming, changelog generation, release tagging. Convention-aware utility replacing ad-hoc git commands.hallucination-guardPost-generation validation — catches hallucinated imports, phantom functions, non-existent packages, typosquatting. Use after code generation, before commit.incidentStructured incident response — triage (P1/P2/P3), contain, verify, root-cause, postmortem. Use when production is down or degraded. Contain BEFORE investigating.integrity-checkDetect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.journalPersistent state tracking across sessions — records decisions with rationale, progress, risks, ADRs to .rune/ files. Called by surgeon, deploy, rescue for cross-session continuity.launchDeploy + marketing orchestrator. Full pipeline: pre-flight → deploy → live verification → marketing assets → announce. Use when shipping to production.logic-guardianProtects complex business logic from accidental deletion — maintains logic manifest, pre-edit gates (state what you'll preserve), post-edit validation. Use on trading bots, payment systems, state…marketingCreate marketing assets — landing copy, social posts, SEO meta, video scripts, slides. Based on actual product capabilities, never aspirational claims.mcp-builderBuild MCP servers from specs — generates tool definitions, resource handlers, test suites. Supports TypeScript (official SDK) and Python (FastMCP). Multi-provider adapter pattern.neural-memoryCross-session cognitive persistence via Neural Memory MCP. Captures decisions, patterns, errors, insights with semantic links. Bridges file-based state (session-bridge) with semantic graph.onboardAuto-generate project context — scans codebase, creates CLAUDE.md + .rune/ directory so every future AI session starts with full context. Use on first session.perfPerformance regression gate — detects N+1 queries, sync-in-async, missing indexes, memory leaks, bundle bloat. Investigate only, does NOT fix. Use before commit or deploy.planCreate structured implementation plans. Produces master plan + phase files for non-trivial work (3+ phases, 5+ files). Use before multi-phase implementation.preflightPre-commit quality gate — catches 'almost right' code. Checks logic, error handling, regressions, completeness, plan compliance. BLOCK verdict stops commit.problem-solverStructured reasoning — applies McKinsey-grade frameworks (5 Whys, Fishbone, First Principles, SCAMPER) with mandatory bias detection. Use for complex multi-factor problems, not simple linear analysis.rescueLegacy refactoring orchestrator for messy codebases (health <40). Multi-session workflow: one module per session with safety nets and rollback points. Use for modernization, not features.researchWeb research — gathers data on technologies, libraries, best practices. Min 3 sources per conclusion, max 5 WebFetch calls. Use for external data gathering, not API docs (use docs-seeker).researcherWeb research and documentation agent. Spawned by research, docs-seeker, trend-scout for external information gathering. Min 3 sources per conclusion.retroEngineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.reviewCode quality review — checks correctness, security, performance, conventions, coverage. Every finding needs file:line. Triggers fix or test for issues found.review-intakeProcess external review feedback — read ALL items first, verify claims against codebase, then implement in priority order. Use when receiving PR comments or code review.reviewerCode review and security analysis agent. Spawned by review, sentinel, preflight for quality and security checks. Every finding must have file:line evidence.safeguardBuild safety nets BEFORE refactoring — characterization tests capturing current behavior, boundary markers, config freeze, rollback tags. MUST run before surgeon.sastStatic analysis tool runner — unified wrapper for ESLint, Semgrep, Bandit, Clippy, govulncheck. Normalized severity output (BLOCK/WARN/INFO). Use for deep security analysis beyond lint.scaffoldAutonomous project bootstrapper — 0 to production-ready. Orchestrates ba → plan → design → fix → test → docs → git → verify in one pipeline. Generated projects MUST build and pass tests.scannerFast codebase scanner for file discovery and pattern matching. Spawned by scout, onboard, and other skills needing project structure analysis. Read-only, max 10 file reads.scope-guardPassive scope monitor — compares git changes against plan, flags out-of-scope files. Advisory only (does not block). Auto-triggered by L1 orchestrators when changes exceed plan.scoutFast codebase scanner — finds files, patterns, dependencies, project structure. Pure read-only. Use BEFORE planning, fixing, reviewing, or refactoring.sentinelSecurity gatekeeper — blocks unsafe code BEFORE commit. Secret scanning, OWASP top 10, dependency audit, destructive command detection. BLOCK verdict stops pipeline.sentinel-envEnvironment pre-flight check — validates OS, runtime versions, tools, ports, env vars, disk space BEFORE coding. Prevents 'works on my machine' failures. Like sentinel but for the environment.sequential-thinkingMulti-variable analysis where factors are interdependent — evaluates in dependency order, checks second-order effects. Use when >3 interacting variables with cascading downstream effects.session-bridgeCross-session context persistence — auto-saves decisions, conventions, progress, instincts to .rune/ files. Loads + integrity-checks at session start. Auto-triggered before compaction.skill-forgeThe skill that builds skills — TDD-driven: baseline test → write skill → verify → refactor → integrate into mesh. Use for creating or editing Rune skills.skill-routerMeta-enforcement layer — routes EVERY agent action through the correct skill before any code is written. Always active. Prevents 'just this once' bypasses.