AgentKit Preview

The intelligent orchestration layer that cuts AI coding costs by 70%

Private Preview — This is the closed development branch of AgentKit. For the public open-source version, see agentkit-ai on npm.

$ npx agentkit-preview@latest init

AgentKit Preview Installer v0.5.21
──────────────────────────

Detecting platforms...
  ✓ Claude Code  (full)
  ✓ Cursor       (partial)

Installing Backend Pro bundle (22 skills)...
  ✓ Skills converted for Claude Code (SKILL.md native)
  ✓ Skills converted for Cursor (.mdc format)
  ✓ Model routing enabled  →  Haiku / Sonnet / Opus
  ✓ Memory graph initialised
  ✓ Quality gates wired into hooks

✓ AgentKit Preview installed!

  Estimated savings:
    Tokens:  ~40,000 → ~5,000/session  (89% reduction)
    Cost:    ~$200/mo → ~$60/mo        (70% reduction)

Before vs After

Real numbers from AgentKit smoke tests, measured across a 50-turn coding session.

| Metric | Without AgentKit | With AgentKit | Improvement | |--------|-----------------|---------------|-------------| | Tokens per session | 45,000 | ~5,000 | 89% less | | Cost per session (Sonnet) | ~$1.35 | ~$0.40 | 70% cheaper | | Skill activation rate | 20% (ad-hoc) | 84% (hook-enforced) | 4× more reliable | | Model used for simple tasks | Sonnet ($0.003/K) | Haiku ($0.00025/K) | 12× cheaper | | Model used for subagents | Sonnet | Haiku (always) | 12× cheaper | | Context at session start | Full 10K token dump | 2K relevant nodes | 80% less noise | | Memory across sessions | None | SQLite graph + handoff | Persistent | | Coding without a plan | Allowed | Blocked by hook | Zero skipped steps |

One Command Install

npx agentkit-preview@latest init

That's it. AgentKit Preview detects your platforms, installs the right skill format for each, wires all hooks, and configures model routing automatically.

Or install globally (then use agentkit as a command anywhere):

npm install -g agentkit-preview
agentkit init

Note: The npm package name is agentkit-preview. After a global install, the CLI command is agentkit.

Looking for the public open-source version? → agentkit-ai on npm (npx agentkit-ai@latest init)

Requirements: Node.js ≥ 18 · Python ≥ 3.9 · Claude Code (for full feature set)

Upgrading from agentkit-ai (public version)?

If you already have the public version installed, run this first to avoid duplicate hooks:

npx agentkit-ai uninstall          # removes public version hooks + CLAUDE.md blocks
npx agentkit-preview@latest init   # install preview fresh

Why: Both packages register hooks into ~/.claude/settings.json. Without uninstalling first, both sets of hooks run on every prompt — causing double skill injection and wasted tokens.

What It Does

AgentKit is a 6-layer runtime that sits between your prompts and the model:

• Layer 0 — Spawn Engine: 3-tier analyzer detects complex tasks and automatically decomposes them into N specialized agents running in parallel waves — no configuration required
• Layer 1 — Skill Router: Classifies every prompt in < 10ms → loads only relevant skills → 45,000 tokens/session down to 5,000 (89% reduction)
• Layer 2 — Memory Graph: SQLite knowledge graph captures files, functions, decisions across sessions → Haiku-compressed handoffs so context survives restarts
• Layer 3 — Token Budget: Auto-routes Haiku / Sonnet / Opus by task complexity + proactive context compaction at 60% fill + real-time cost dashboard in your status bar
• Layer 4 — Workflow Engine: Enforces Research → Plan → Execute → Review → Ship via hooks — can't skip planning, quality gates (syntax/lint/types/tests) run after every edit
• Layer 5 — Platform Layer: One SKILL.md file auto-converted to 10 platform formats — Cursor .mdc, Codex AGENTS.md, Gemini CLI config, and more

Works With

| Platform | Support | Install format | |----------|---------|----------------| | | Full — skills + hooks + memory + routing | Native SKILL.md | | | Skills + model routing rules | .cursor/rules/*.mdc | | | Skills via system prompt | .gemini/GEMINI.md | | | Skills via Cascade rules | .windsurf/rules.md | | | Skills + native TUI plugin + slash commands | System prompt + TUI plugin | | | Skills as plugins | .kilo/plugins/*.yaml | | | Skills injected | AGENTS.md | | | Skills as conventions | .aider.conf.yml | | | Skills as context | .augment/context.md | | | Full plugin system | .antigravity/plugins/ |

Ruflo: AgentKit makes your Ruflo swarms 3× cheaper by routing worker agents to Haiku and injecting only relevant skills per agent.

OpenCode Integration

AgentKit ships a native TUI plugin for OpenCode that lives inside the terminal UI — not just in the system prompt.

What you get

| Feature | Detail | |---------|--------| | AgentKit agent persona | agentkit ⚡ appears in OpenCode's agent list — press tab to switch to it | | Active agent label | Status bar shows Agentkit in orange when selected | | Startup toast | ⚡ AgentKit v0.5.x Active — 54 skills loaded appears on every launch | | /agentkit | Status command — shows version, skill count, session cost | | /agentkit-task | Pre-fills the prompt with @agentkit-task: — type your task and press Enter | | /agentkit-analytics | Shows cost & usage info | | /ak | Alias for /agentkit | | /ak-task | Alias for /agentkit-task |

The AgentKit Agent Persona

After install, AgentKit registers itself as a named agent in OpenCode's agent switcher. Press tab → select agentkit ⚡ to activate it. Once active, the status bar shows Agentkit in orange — you're now running with full AgentKit skill-routing and workflow enforcement on every message.

Install (preview users)

Setup instructions are provided upon access approval. Contact @Ajaysable123 to request access.

Public version: npx agentkit-ai@latest init (open-source, separate from this preview branch)

How to assign a task

Option A — via agent + prompt (recommended):

1. Press tab → select agentkit ⚡
2. Type your task directly and press Enter

Option B — via slash command:

1. Press ctrl+p → type /agentkit-task → select it
2. The prompt pre-fills with @agentkit-task:
3. Type your task after the prefix and press Enter

Both options activate the full AgentKit workflow: Research → Plan → Execute → Review → Ship.

Manual plugin install (optional)

If auto-detection misses OpenCode, register the plugin directly:

opencode plugin "/path/to/AgentKit/platform/opencode-plugin" --global --force

Find the path with: npm root -g agentkit-ai → append /platform/opencode-plugin.

Dynamic Agent Spawning

AgentKit v0.5.4 adds a zero-config spawn engine that automatically detects when a task needs multiple agents and orchestrates them for you.

$ claude "Build a REST API with auth, tests, and a security audit"

[AgentKit] Multi-agent task detected (confidence: 0.90)
[AgentKit] Spawning 5 agents in 4 waves...

Wave 1 →  architect  (opus-4.6)      Design schema + endpoints
Wave 2 →  writer     (haiku-4.5)     Implement API + auth          [waits: architect]
Wave 3 →  tester     (haiku-4.5)     Write pytest suite            [waits: writer]
         security   (sonnet-4.6)    OWASP audit                   [waits: writer]
Wave 4 →  reviewer   (sonnet-4.6)    Final code review             [waits: writer + tester]

• 3-tier detection: keyword signals (<5ms) → heuristic scoring (<10ms) → Haiku LLM fallback (~$0.0003) for ambiguous cases
• Smart model routing per role: Architect gets Opus, implementation gets Haiku, security/review get Sonnet
• DAG execution: parallel where possible, sequential where dependencies require it
• Recursion-safe: spawned agents never re-spawn (infinite loop prevention built-in)

How AgentKit Compares

| Feature | AgentKit | Superpowers | claude-mem | ClaudeFast | |---------|----------|-------------|------------|------------| | Dynamic agent spawning | ✅ Auto-detects, N agents, DAG waves | ❌ | ❌ | ❌ | | Smart skill loading | ✅ Auto-routed, 89% token reduction | ✅ Manual SKILL.md | ❌ | ❌ | | Skill library | ✅ 50 skills, 7 role bundles | ❌ BYO only | ❌ | ❌ | | Persistent memory | ✅ SQLite graph + session handoffs | ❌ | ✅ Basic | ❌ | | Auto model routing | ✅ Haiku/Sonnet/Opus by complexity | ❌ | ❌ | ⚠️ Basic | | Workflow enforcement | ✅ Research→Plan→Execute→Review→Ship | ⚠️ Suggested only | ❌ | ❌ | | Quality gates | ✅ syntax+lint+types+tests on every edit | ❌ | ❌ | ❌ | | Multi-platform | ✅ 10 platforms, 1 config | ❌ Claude Code only | ❌ | ❌ | | Subagent cost routing | ✅ Per-role model (12× cheaper) | ❌ | ❌ | ❌ | | Cost dashboard | ✅ Real-time status bar | ❌ | ❌ | ✅ | | npx install | ✅ One command | ❌ Manual | ❌ Manual | ❌ |

CLI Reference

CLI commands below are available to approved preview users. Install instructions provided upon access.

agentkit init              # Detect platforms → install
agentkit sync              # Re-sync after adding skills
agentkit status            # Health check + cost summary
agentkit costs --days 7    # Weekly cost analytics
agentkit skills list       # Browse all 50 skills
agentkit workflow status   # Current Research/Plan/Execute state
agentkit workflow approve  # Approve plan → unlock coding
agentkit detect            # Show detected AI coding tools
agentkit uninstall         # Remove all AgentKit files
agentkit uninstall --purge # Also delete runtime data (costs/memory/state)

Skill Bundles

Pick a bundle at install time or pass --bundle <name>:

| Bundle | Skills | Best for | |--------|--------|----------| | backend-pro | python-debugger, go-debugger, pytest, rest-api, grpc, sql, mongodb, redis, auth, owasp, docker, nginx + 10 more | Python/Go backend engineers | | frontend-wizard | js-debugger, jest, cypress, playwright, react, vue, nextjs, css, state-mgmt, a11y, graphql + 2 more | Frontend / React developers | | full-stack-hero | All 50 skills | Full-stack teams | | ai-engineer | llm-prompting, rag-pipeline, function-calling, agent-design, eval-testing + 5 more | LLM / AI application developers | | devops-master | docker, kubernetes, github-actions, terraform, monitoring, nginx + 3 more | DevOps / Platform engineers | | data-scientist | pandas, data-viz, ml-pipeline, sql, pytest + 2 more | Data scientists / ML engineers | | mobile-dev | react-native, flutter, rest-api, auth-jwt + 3 more | Mobile developers |

All 50 Skills

| Category | Skills | |----------|--------| | Debugging | python-debugger, js-debugger, go-debugger, network-debugger | | Testing | tdd-workflow, jest-testing, pytest-workflow, cypress-e2e, playwright-testing, contract-testing | | API | rest-api, graphql, grpc, openapi-design, webhook-design | | Database | sql-query, prisma-orm, mongodb, redis-caching, database-migrations | | Frontend | react-patterns, nextjs-patterns, css-layout, vue-patterns, state-management, accessibility | | DevOps | docker, kubernetes, github-actions, terraform, monitoring-observability, nginx-config | | Security | auth-jwt, owasp-top10, secrets-management, api-security | | Refactoring | clean-code, performance-optimization, code-review, legacy-modernization | | AI Engineering | llm-prompting, rag-pipeline, function-calling, agent-design, eval-testing | | Data Science | pandas-workflow, data-visualization, ml-pipeline | | Mobile | react-native, flutter |

Built on the shoulders of giants: Superpowers (108K ⭐) · claude-mem (39.9K ⭐) · awesome-claude-code (30.9K ⭐)

GitHub · Public npm · Proprietary License