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 skills add bikeread/promethos --skill orchestrate-agent-subagentsgit clone --depth 1 https://github.com/bikeread/promethosWrote 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/skills/bikeread/promethos/orchestrate-agent-subagents)<a href="https://agentmods.dev/skills/bikeread/promethos/orchestrate-agent-subagents"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/orchestrate-agent-subagents/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bikeread/promethos/orchestrate-agent-subagents"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/orchestrate-agent-subagents.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00027 | $0.00708 |
| Opus 5.5 | $0.00011 | $0.00283 |
| Sonnet 5.5 | $0.00005 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
orchestrate-agent-subagents 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 2mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Use subagents only when they create real leverage, with clear ownership and safe integration.
Inputs
- Main task shape
- Chosen architecture or explicit decision that delegation is warranted
- Available agent capabilities
- Shared context and integration constraints
Non-Goals
- Making the top-level single-agent vs multi-agent architecture choice
- Using subagents for status or novelty
- Delegating urgent blocking work without a clear handoff
Workflow
Trigger signals
- Architecture calls for multiple agents but ownership boundaries are not drawn
- User asks "怎么分工" or "how should we split the work"
- Subagents are being launched without clear context contracts or merge rules
1. Restate the delegation boundary
Confirm what part of the system or workflow is already designated for delegation and what must remain local to the coordinating agent. Success criteria: The orchestration work starts from an explicit delegation decision instead of reopening the architecture choice.
2. Split the work into owned units
Assign each subagent a distinct responsibility, output artifact, and write scope. Success criteria: Ownership boundaries prevent duplicated work and merge conflicts.
3. Define context and handoff contracts
Specify what context each subagent receives, what it must return, and what it must not assume. Success criteria: The delegation plan has minimal but sufficient context and clear artifact expectations.
4. Freeze permission, approval, and side-effect inheritance
State which parent-agent permission limits, approval requirements, write scopes, and side-effect restrictions are inherited by each subagent. Specify whether a subagent may execute side effects directly or may only return proposals for the coordinating agent to act on. Success criteria: Delegation does not silently widen autonomy, tool access, or side-effect authority.
5. Define synchronization and merge rules
State when results are needed, how conflicts are resolved, and what main-agent review is required before integration. Success criteria: The orchestration includes a predictable reintegration path instead of ad hoc waiting and trust.
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.
- 2mo ago First seen · 92 lines · 27 tokens per session scan A 89653c624856
orchestrate-agent-subagents is a skill published in the GitHub repository bikeread/promethos (33 stars, last pushed 7mo ago), licensed MIT. It adds 27 tokens to every session and 708 once invoked, about $0.0001 per session on Opus 5.5. 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.
orchestrate-agent-subagents compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| orchestrate-agent-subagentsbikeread/promethos | Skill | 33 | 7mo ago | MIT | A | 27 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |