archon-os

Plugin archon-os from marketplace archon in nguyenthienthanh/archon. Commands read from the repo's manifest — 6 days ago.

Skills (45)

• agent-detector

  CRITICAL: MUST run for EVERY message. Detects agent, complexity, AND model automatically. Without this, tasks route to wrong agents and use wrong models, degrading quality and wasting tokens.

• api-designer

  Designs RESTful APIs with endpoint naming, versioning strategies (URL path, header-based), pagination (offset and cursor), error response schemas, and OpenAPI conventions. Use when the user asks about REST API design, creating endpoints, URL structure, API versioning, status codes, Swagger, or OpenA

• bugfix-quick

  Fast bug fixes with root cause investigation + TDD. Enforces 'no fix without root cause' discipline and verification protocol. Without this skill, fixes are applied at symptoms instead of sources, and bugs return.

• chain-of-verification

  Draft → generate verification questions → answer independently via tools → revise. Catches hallucinated facts in reports and reviews. MANDATORY for Phase 4 security/test claims. Paper: Dhuliawala et al. 2023.

• code-map

  Reverse-dependency lookup — \"I am about to change this file, what breaks?\" Use when assessing the blast radius of an edit, finding every importer of a module (including the ones that never name it), or checking what the startup code-map digest was derived from. Not for finding text: grep is better

• code-reviewer

  8-aspect evidence-based code review/audit (security, correctness, compatibility, architecture, error handling, test gaps, type safety, simplicity) built on Google eng-practices, OWASP Top 10:2025, CWE Top 25, SemVer. Every finding needs file:line + a concrete failure scenario. Use when the user asks

• code-simplifier

  Detect and simplify overly complex code. Apply KISS principle - less is more.

• conflict-detector

  L1-L4 conflict detection between a proposed T4 task and pending-confirm sibling tasks. L1 (file overlap) + L2 (function/region overlap) ship in v3.7.0-beta.2 as deterministic bash. L3 (semantic LLM) + L4 (architectural LLM) are stubbed for v3.7.0-rc.1.

• deep-debugging

  Systematic debugging protocol for bugs that resist quick fixes. Use bisection, hypothesis trees, and scientific method when a bug isn't obvious from the stack trace. Goes beyond bugfix-quick for production-grade root cause analysis.

• design-expert

  UI/UX design expertise — component design, design system selection, responsive layout. Includes auto-detection from package.json and Context7 integration for library docs.

• design-tokens

  Generate a cohesive color-token system from ONE OKLCH brand hue — primary/secondary/background/foreground/muted/border with semantic light + dark, emitted as a Tailwind v4 @theme block or a CSS-variables fallback. Use when starting a design system, defining brand colors, setting up theming/dark-mode

• design-vision-loop

  Vision feedback loop for UI — render the running UI, screenshot it across viewports + dark mode, run deterministic gates then a multimodal critique against the design system, and iterate until it passes. Use after building or changing a UI component/page, when asked to 'check the UI', make it 'look

• documentation

  Create Runbooks for operational documentation. For ADRs, tech specs, requirements, LLD and technical analysis use the tech-writing skill instead.

• extension-detector

  Detects when a new project-level skill / rule / command would reduce friction. Asks the user for confirmation before creating anything. NEVER writes plugin-level files — only `.claude/skills/`, `.claude/rules/`, `.claude/commands/` in the user's project.

• failure-classifier

  Classifies execution failures into F1-F5 (transient/local-logic/local-design/story-level/architectural). Outputs JSON with class, confidence, evidence, and recommended action. Deterministic rule-based classifier; no LLM call.

• framework-expert

  Unified framework expertise bundle. Lazy-loads relevant framework patterns (React, Vue, Angular, Next.js, Node.js, Python, Laravel, Go, Flutter, React Native, TypeScript) based on detected tech stack.

• frontend-aesthetics

  Anti-AI-slop taste layer for UI output — distinctive typography, dominant+accent color hierarchy, and implementation-matched polish. Use when building or restyling a UI/landing/component that should look designed rather than defaulted, or when the user asks for something 'beautiful', 'distinctive',

• git

  Token-efficient git operations with security scanning and auto-split commits, plus auto-creating git worktrees to isolate workflow changes — merge on success, discard on failure.

• independent-verifier

  Second opinion on another agent's result from a cheap model. Deterministic scope gate first (free), then k=3 blind Haiku samples; confidence comes from AGREEMENT, never from self-report. One verdict back, no debate. May only lower confidence.

• mcp-security-auditor

  On-demand audit of MCP usage. Reads the MCP audit log (mcp-audit.jsonl) written by the mcp-call-gate hook, surfaces blocked calls, rate-limit hits, suspicious input patterns. Companion to mcp-call-gate hook (which produces the audit log).

• migration-helper

  Guide safe database and code migrations with zero-downtime strategies.

• monorepo

  Detect and navigate monorepos correctly. Use when working with repos containing multiple packages (pnpm/yarn/npm workspaces, Turborepo, Nx, Lerna). Ensures commands run in correct package scope, dependencies are routed properly, and cross-package changes are coordinated.

• motion-design

  Restrained, accessible web motion — Framer Motion declarative patterns and CSS-only staggered reveals for high-impact moments, always bundle-aware and reduced-motion-safe. Use when adding animation/transitions to a UI (entrance reveals, list stagger, page/route transitions, micro-interactions) or wh

• perf-profiling

  Systematic performance profiling and optimization across frontend (Core Web Vitals, code splitting, lazy loading), backend (N+1 queries, async), and database (EXPLAIN ANALYZE, indexing) layers. Use when the user reports slow code, latency, memory leaks, needs to benchmark, or wants to speed up an ap

• permanent-memory-loader

  Loads permanent_memory.md summary lines (≤120 always-loaded tokens, hard cap 200). Surfaces durable wisdom from past Epics into the current session. Silent if .claude/memory/ does not exist.

• plan-archivist

  Compresses a completed plan-tree branch into .claude/plans/archive/{NODE_ID}.summary.md. Removes the original node files (preserved by checkpoint history). Reduces always-loaded surface area as features ship.

• plan-loader

  Loads minimum hierarchical plan context (.claude/plans/) for current execution focus. Auto-invokes every session when plans exist. Stays under 800 always-loaded tokens regardless of plan tree size.

• plan-orchestrator

  Route hierarchical-planning intents to the correct backing script. Use when the user invokes /archon-os:plan (with or without subcommand), mentions plan verbs (expand/next/replan/promote/archive/freeze/thaw/undo/status/conflicts), or types a plan-vocabulary bare word with .claude/plans/active.json p

• plan-validator
• preflight-validator
• problem-solving
• project-context-loader
• prompt-evaluator
• reasoning-trace-recorder
• refactor-expert
• run-orchestrator
• scalable-thinking
• self-consistency
• self-healing-orchestrator
• self-improve
• session-continuation
• stitch-design
• tech-writing
• test-writer
• tree-of-thoughts

Slash commands (27)

• /archon-os:README
• /archon-os:af
• /archon-os:archon
• /archon-os:check
• /archon-os:dashboard
• /archon-os:design
• /archon-os:extend
• /archon-os:heal
• /archon-os:help
• /archon-os:mcp
• /archon-os:plan-archive
• /archon-os:plan-conflicts
• /archon-os:plan-expand
• /archon-os:plan-freeze
• /archon-os:plan-next
• /archon-os:plan-promote
• /archon-os:plan-replan
• /archon-os:plan-status
• /archon-os:plan-thaw
• /archon-os:plan-undo
• /archon-os:plan
• /archon-os:preflight
• /archon-os:project
• /archon-os:research
• /archon-os:reset-session
• /archon-os:run
• /archon-os:trace

Subagents (16)

• README
• architect

  System design, database schema, API endpoints, backend architecture. Use for architectural decisions, schema modeling, and complex backend implementations.

• conflict-arbiter

  Adjudicates detected conflicts between plan-tree tasks. Decides freeze | sequential | replan | escalate per spec §21.5. Read-only on code; writes only to .claude/plans/conflicts.jsonl + history.jsonl.

• devops

  Docker, Kubernetes, CI/CD, infrastructure-as-code, cloud deployment. Use for containerization, pipelines, and deployment strategy.

• epic-summarizer

  Distills a completed Epic (T2 Feature done) into a permanent_memory.md section. Captures architectural decisions, gotchas, anti-patterns, conflicts. Writes ONLY to .claude/memory/. Confidence-scored: items below 0.7 land in a Tentative subsection.

• feature-architect

  T2 (Feature) decomposition specialist for hierarchical planning. Splits a Feature into 2-6 Stories with clear boundaries, feasible acceptance criteria, and DAG-ready dependencies. Read-only on code; writes only to .claude/plans/features/<id>/ tree.

• frontend

  Frontend frameworks (React/Vue/Angular/Next.js), design systems, accessibility. Use for UI implementation, component work, and responsive design.

• lead

  Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.

• master-planner

  Stateful kernel controller for the plan tree. Owns plan persistence at .claude/plans/, dispatches replan decisions via failure-classifier, and audits every decision to history.jsonl. NEVER executes tasks directly — always delegates to specialist agents (architect, frontend, mobile, tester, security,

• mobile

  React Native / Flutter / Expo mobile development. Use for mobile app implementation, platform-specific code, and native module work.

• replanner

  Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.

• scanner

  Project detection, config loading, context tracking. Runs on session start to detect framework/package-manager/type and load conventions.

• security

  OWASP + vulnerability + SAST review. Use for security audits, auth/crypto code review, and threat assessment. READ-ONLY — never writes code.

• story-planner

  T3 (Story) decomposition for hierarchical planning. Splits a Story into 1-6 atomic Tasks. Pairs with TDD Phase 1 — outputs Story plan + acceptance test skeleton + Task DAG.

• strategist

  Business strategy, MVP scoping, ROI evaluation. Use in Phase 1 Deep tasks to challenge requirements and evaluate business case. READ-ONLY — analysis only.

• tester

  Test strategy, automation, TDD enforcement, coverage analysis. Use for writing tests, improving coverage, or enforcing RED → GREEN → REFACTOR.

MCP servers (6)

• context7

  runs: npx -y @upstash/context7-mcp

• playwright

  runs: npx -y @playwright/mcp@latest --headless --isolated

• vitest

  runs: npx -y @djankies/vitest-mcp

• firebase

  runs: npx -y firebase-tools@latest experimental:mcp

• figma

  runs: npx -y figma-developer-mcp --stdio

• slack

  runs: npx -y @modelcontextprotocol/server-slack

Hooks (30)

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/dispatch.cjs" '>session-start' '>firebase-cleanup' '>playwright-reaper' '>workflow-edit-learn' '>changelog-notify' '>session-start-restore-active'

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/compact-handoff.cjs" --resume 2>&1

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/code-map-digest.cjs" --session-start

• SessionStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/dispatch.cjs" '>update-check' '>test-pattern-extractor' '>pending-confirm-timeout'

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/dispatch.cjs" scout-block research-write-guard '>pre-execute-load-plan-context' '>tool-call-tracer+CLAUDE_HOOK_PHASE=pre' pre-flight-validate

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/pre-dispatch-conflict-check.cjs" 2>&1

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/mcp-call-gate.cjs"

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/commit-attribution.cjs"

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/task-track-model.cjs" 2>&1

• PreToolUse

  if ! compgen -G '.claude/project-contexts/*/project-config.yaml' > /dev/null 2>&1; then echo '💡 Reminder: Run project:init to create project context before generating code' >&2; fi

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/security-critical-warn.cjs"

• PreToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/phase-checkpoint.cjs" 2>&1

• PostToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/learning-dispatch.cjs" 2>&1

• PostToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/dispatch.cjs" '>lint-autofix' security-scan design-conformance auto-test-runner

• PostToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/dispatch.cjs" token-tracker '>post-execute-update-node' '>tool-call-tracer+CLAUDE_HOOK_PHASE=post'

• PostToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/tdd-red-failure-tracker.cjs" 2>&1

• PostToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/task-clear-model.cjs" 2>&1

• PostToolUse

  node "${CLAUDE_PLUGIN_ROOT}/scripts/verify-claim.cjs" --hook

• PostToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/dispatch.cjs" '>feature-done-trigger-archive' '>session-reset-trigger' '>post-execute-conflict-rescan' '>run-deliverables-scaffold'

• PostToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/code-map-digest.cjs" --post-tool-use

• PostToolUse

  node "${CLAUDE_PLUGIN_ROOT}/hooks/json-toon-projector.cjs" 2>&1

• UserPromptSubmit

  node "${CLAUDE_PLUGIN_ROOT}/hooks/dispatch.cjs" thinking-boost prompt-reminder

• UserPromptSubmit

  node "${CLAUDE_PLUGIN_ROOT}/hooks/dispatch.cjs" '>auto-learn' scope-drift prompt-logger '>jira-auto-fetch' bare-word-router plan-escalation-check

• SubagentStart

  node "${CLAUDE_PLUGIN_ROOT}/hooks/subagent-init.cjs"

• TeammateIdle

  node "${CLAUDE_PLUGIN_ROOT}/hooks/teammate-idle.cjs"

• TaskCompleted

  node "${CLAUDE_PLUGIN_ROOT}/hooks/task-completed.cjs"

• Stop

  node "${CLAUDE_PLUGIN_ROOT}/hooks/dispatch.cjs" '>compact-handoff' '>rate-limit-check'

• Stop

  node "${CLAUDE_PLUGIN_ROOT}/hooks/session-metrics.cjs" 2>&1

• Stop

  node "${CLAUDE_PLUGIN_ROOT}/hooks/context-auto-refresh.cjs" 2>&1

• PreCompact

  node "${CLAUDE_PLUGIN_ROOT}/hooks/compact-handoff.cjs" --pre-compact 2>&1

Similar plugins