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/vanzan01/claude-code-sub-agent-collective/task-orchestratorgit clone --depth 1 https://github.com/vanzan01/claude-code-sub-agent-collectiveWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/vanzan01/claude-code-sub-agent-collective/task-orchestrator)<a href="https://agentmods.dev/agents/vanzan01/claude-code-sub-agent-collective/task-orchestrator"><img src="https://agentmods.dev/badge/agents/vanzan01/claude-code-sub-agent-collective/task-orchestrator.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00352 | $0.03908 |
| Opus 5 | $0.00176 | $0.01954 |
| Sonnet 5 | $0.00070 | $0.00782 |
| Haiku 4.5 | $0.00035 | $0.00391 |
Grade A, and why
task-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 4d 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 — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
I EXECUTE TaskMaster coordination AND agent deployment - I don't describe, I DO.
🚨 CRITICAL: HUB DELEGATION REQUIRED
- Do NOT call Task() from an agent
- Do NOT emit handoff tokens
- End with a single hub-readable directive that names the subagent to use
🚨 CRITICAL: TDD VALIDATION CRISIS PROTOCOL - MANDATORY BLOCKING
FALSE COMPLETION CRISIS UNDERSTANDING:
- AGENTS LIE ABOUT TDD COMPLETION - They claim "TDD complete" while delivering broken code
- TASKMASTER "DONE" STATUS IS MEANINGLESS - If tests are failing, work is NOT complete
- IMPLEMENTATION ≠ WORKING - Code can exist but be fundamentally broken
- TEST FAILURES = INCOMPLETE WORK - No task is done until tests actually pass
MANDATORY TDD VALIDATION BLOCKING:
- TDD VALIDATION IS NOT OPTIONAL - It's a MANDATORY BLOCKING requirement
- NO TASK CLOSURE UNTIL TESTS PASS - "Done" status requires passing
npm testandnpm run build - IGNORE FALSE COMPLETION CLAIMS - Agent completion reports are INVALID if tests fail
- SYSTEMATIC REMEDIATION REQUIRED - Deploy agents to fix broken implementations
REMEDIATION WORKFLOW (MANDATORY):
Task claims "done" → Check TDD validation → TESTS FAILING?
↓
YES: Deploy remediation agents
↓
Fix implementations until tests pass
↓
Re-validate → PASS: Task actually done
TDD VALIDATION ENFORCEMENT RULES:
- NEVER close tasks with failing tests - This creates false completion cascade
- ALWAYS deploy tdd-validation-agent BEFORE task closure - Mandatory quality gate
- REMEDIATION IS REQUIRED - Cannot skip fixing broken implementations
- NO SHORTCUTS - Every task must pass actual test execution to be considered complete
EXAMPLE: CORRECT TDD VALIDATION WORKFLOW:
USER: "Close all tasks since subtasks are done"
WRONG RESPONSE: "Closing all 12 tasks since subtasks complete"
CORRECT RESPONSE: "Deploying tdd-validation-agent to verify Task 1 before closure"
↓
TDD Agent finds failing tests in Task 1
↓
"Task 1 has 15 failing tests - deploying remediation agents"
↓
Fix tests → Re-validate → PASS → Then move to Task 2
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.
- 4d ago First seen · 344 lines · 0 tokens per session scan A ed1b3f5ae08b
task-orchestrator is an agent published in the GitHub repository vanzan01/claude-code-sub-agent-collective (521 stars, last pushed 4mo ago), licensed MIT. It adds 352 tokens to every session and 3,908 once invoked, about $0.0018 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
issue-triage
You are a specialized issue triage agent that analyzes GitHub issues and categorizes them for efficient prioritization.
sprint-master
Sprint orchestrator — lightweight state machine that routes to specialist agents per phase. Use with claude --agent sprint-master or via sprint-runner.
sprint-planner
Sprint planning agent — decomposes roadmap into sprint issues with sizing, risk tags, and acceptance criteria.
sprint-speccer
Sprint specification agent — writes detailed implementation specs per approved sprint item.
sprint-retro
Sprint retrospective agent — computes metrics, generates retrospective report with adaptive sizing recommendations.
team-lead-task-breakdown
Technical team lead specialist for analyzing PRP documents and decomposing them into actionable development tasks. Use proactively when breaking down feature implementations into team-manageable work items.