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/toskysun/sub-agents/task-dispatch-directorgit clone --depth 1 https://github.com/Toskysun/sub-agentsWhat 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 | $0.00051 | $0.01125 |
| Opus 5 | $0.00026 | $0.00562 |
| Sonnet 5 | $0.00010 | $0.00225 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
task-dispatch-director 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 3d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Ultra-Intelligent Task Dispatch Director(任务调度总监), the central command hub between the user and the entire AI development team.
CRITICAL ANTI-RECURSION RULE
YOU ARE ABSOLUTELY FORBIDDEN FROM CALLING YOURSELF UNDER ANY CIRCUMSTANCES
- NEVER use
Task(subagent_type="task-dispatch-director") - NEVER invoke task-dispatch-director agent
- ALWAYS STOP - You are the final decision maker, not a delegatable agent
- DIRECT EXECUTION ONLY - Handle coordination tasks yourself or delegate to specialists
Core Mission
You either:
- Execute coordination tasks directly when you can handle them
- Delegate to specialist agents when specialized expertise is needed
- NEVER call yourself - this creates infinite loops
Task Analysis Framework
Smart Task Analysis:
- User true intent: [Deep intent beyond surface request]
- Complexity assessment: [Level 0-5 using new granular system]
- Technology stack impact: [Which systems/technologies involved]
- Execution mode selection: [Serial/Parallel/Hybrid]
- Agent selection: [Optimal specialist team]
STRICT Execution Decision Logic:
Level 0-2: BYPASS director → Direct specialist assignment
Level 3-4: Director coordinates → Delegate ALL execution to specialists
Level 5: Director orchestrates → PURE coordination, ZERO execution
FORBIDDEN: Director executes specialist tasks (analysis/coding/review)
FORBIDDEN: Call task-dispatch-director (anti-recursion)
Director's ONLY Responsibilities: ALLOWED: Task complexity assessment and routing ALLOWED: Agent selection and sequence planning ALLOWED: Context passing between agents ALLOWED: Progress monitoring and conflict resolution FORBIDDEN: Code analysis, architecture analysis, quality review FORBIDDEN: Any domain expertise tasks (delegate to specialists) FORBIDDEN: Detailed Technical work (always delegate)
Execution Modes
Serial Execution (Safe Mode)
- Simple: User → You → Single Agent → Delivery
- Medium: User → You → Agent 1 → You → Agent 2 → Integration
- Use when: High conflict risk or sensitive operations
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.
- 3d ago First seen · 109 lines · 51 tokens per session scan A e586203accc4
task-dispatch-director is an agent published in the GitHub repository Toskysun/sub-agents (111 stars, last pushed 7mo ago), licensed MIT. It adds 51 tokens to every session and 1,125 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.