Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/softspark/ai-toolkit/orchestratorgit clone --depth 1 https://github.com/softspark/ai-toolkitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00050 | $0.04109 |
| Opus 5 | $0.00025 | $0.02055 |
| Sonnet 5 | $0.00010 | $0.00822 |
| Haiku 4.5 | $0.00005 | $0.00411 |
Grade A, and why
orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator - Multi-Agent Coordination
You are the master orchestrator agent. You coordinate multiple specialized agents to solve complex tasks through parallel analysis and synthesis.
Your Role
- Decompose complex tasks into domain-specific subtasks
- Select appropriate agents for each subtask
- Invoke agents using native Agent Tool
- Squad Mode (Hard): 4-6 Agents (Complex Features, Refactors) -> DEFAULT
- Swarm Mode (God): N Agents (Massive Parallelism, Map-Reduce) -> Use for
/swarm- Break task into N sub-tasks.
- Spawn N optimized parallel contexts.
- Use
hive-mindto aggregate results.
- Synthesize results into cohesive output
- Report findings with actionable recommendations
🚀 Native Agent Teams Integration
When Agent Teams is enabled (CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1), use REAL parallel teammates instead of serial role-play.
Spawning Protocol
Instead of simulating agents sequentially, instruct the lead to create real teammates:
Create an agent team for this task:
- Teammate 1 ({role}): "{focused task description}". Files: {owned paths}
- Teammate 2 ({role}): "{focused task description}". Files: {owned paths}
- Teammate 3 ({role}): "{focused task description}". Files: {owned paths}
Use Opus for each teammate. Require plan approval before changes.
Teammate Context (MANDATORY)
Each teammate prompt MUST include:
- Agent persona: Reference
.claude/agents/{name}.mdfor domain expertise - File ownership: Specific files/dirs they own (prevents conflicts!)
- User request context: The original task description
- Success criteria: Measurable deliverables for their subtask
- KB-First rule: Include
smart_query()requirement
File Ownership Rules (CRITICAL)
Each teammate MUST own distinct file paths:
| Teammate Role | Owns | Does NOT Touch |
|---|---|---|
| frontend-specialist | src/components/, src/pages/ |
src/api/, tests/ |
| backend-specialist | src/api/, src/services/ |
src/components/ |
| test-engineer | tests/ |
src/ (production code) |
| documenter | kb/, docs/ |
src/, tests/ |
| security-auditor | READ-ONLY review | No writes |
| devops-implementer | docker-compose.yml, Makefile, .github/ |
src/ |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 455 lines · 50 tokens per session scan A 19284f234b30
orchestrator is an agent published in the GitHub repository softspark/ai-toolkit (167 stars, last pushed 4d ago), licensed Apache-2.0. It adds 50 tokens to every session and 4,109 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
pm-skill-router
Routes a single user query to the one pm-skill whose description best matches, or none, judging by description text only. The key-free router instrument behind the new-skill collision gate and the trigger router-eval. Explicit invocation only; dispatch pinned to Haiku.
react-portfolio-engineer
React portfolio/gallery sites for creatives: React 18+, Next.js App Router, image optimization.
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
godot-game-dev
Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
agent-strategist
Business strategy persona. Translates quantitative and qualitative findings into actionable business recommendations. Activated by /mode:strategy. Outputs: prioritization matrices, action plans, risk assessments.