subagent-external-wait-orchestrator-takeover

subagent-external-wait-orchestrator-takeover is a skill for Claude Code from wan-huiyan/agent-traffic-control. It costs 341 tokens per session (3,082 once invoked), scanned A, original, MIT.

A workflow for taking over after a subagent has finished its main work but is still waiting for an outside event, such as a CI job, deployment, or long test run. It separates active work from repeated status polling.

In plain words
What is it for?
Use it when an agent must wait for CI, an automated deployment, a cloud rollout, or another external process before final verification.
Why use it?
Repeated polling keeps both the subagent and the coordinating agent occupied without adding useful work. This approach lets the coordinator handle the wait more efficiently.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents; positional $N argument; mentions Claude Code.

Part of the agent-traffic-control plugin — 105 skills shipped together

Good fit Use it when an agent must wait for CI, an automated deployment, a cloud rollout, or another external process before final verification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wan-huiyan/agent-traffic-control/subagent-external-wait-orchestrator-takeover
Install

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.

Any agent
npx skills add wan-huiyan/agent-traffic-control --skill subagent-external-wait-orchestrator-takeover
Clone the repo
git clone --depth 1 https://github.com/wan-huiyan/agent-traffic-control

Made for: Claude Code.

Or install agent-traffic-control, the plugin that ships this one along with the rest of its 105 skills.

Wrote 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.

agentmods badge for subagent-external-wait-orchestrator-takeover

README.md
[![agentmods](https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/subagent-external-wait-orchestrator-takeover/github.svg)](https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/subagent-external-wait-orchestrator-takeover)
Your own site
<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/subagent-external-wait-orchestrator-takeover"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/subagent-external-wait-orchestrator-takeover/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.

agentmods 80×15 button for subagent-external-wait-orchestrator-takeover

Your own site · 80×15
<a href="https://agentmods.dev/skills/wan-huiyan/agent-traffic-control/subagent-external-wait-orchestrator-takeover"><img src="https://agentmods.dev/badge/skills/wan-huiyan/agent-traffic-control/subagent-external-wait-orchestrator-takeover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 341 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,082 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00341 $0.03082
Opus 5 $0.00170 $0.01541
Sonnet 5 $0.00068 $0.00616
Haiku 4.5 $0.00034 $0.00308

Measured 5d ago against content hash 1274afa4af5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

subagent-external-wait-orchestrator-takeover 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 5d 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.

plugins/agent-traffic-control/skills/subagent-external-wait-orchestrator-takeover/SKILL.md · 277 lines

How it starts

The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagent external-wait → orchestrator-takeover

Problem

You dispatch a subagent with a brief that includes both substantive work AND a final verification step gated on an external event:

"1. Implement … 2. Open PR … 3. Merge … 4. Verify auto-deploy: poll GHA workflow + gcloud run revisions list until new revision is active."

Step 4 is wait work — the subagent has nothing to compute, only to wait and check. The harness keeps the agent task open during this wait, and each heartbeat / external signal wakes the agent for a tiny no-op cycle:

status: completed · tool_uses: 0 · duration_ms: 2000 · result: "Still polling."
status: completed · tool_uses: 0 · duration_ms: 2200 · result: "In progress."
status: completed · tool_uses: 0 · duration_ms: 1800 · result: "Continuing to wait."
... × 10-20 ...

Each cycle costs:

  • Subagent: ~100-300 tokens of additional context per wake (small but accumulates)
  • Orchestrator: ~one full turn to acknowledge the notification (large — the orchestrator's context is bigger and every reply costs)

The orchestrator's response cost dwarfs the subagent's polling cost. Over a 13-minute Cloud Build wait, this can be ~10-20 orchestrator turns of "still polling, will report when done" — a non-trivial budget tax for zero work.

Context / Trigger Conditions

ALL of the following:

  1. You dispatched a subagent (Task tool with run_in_background: true)
  2. The subagent's brief includes a "wait + verify" step at the end
  3. You're seeing repeated <task-notification> events from that agent with:
    • status: completed
    • tool_uses: 0
    • Short duration_ms (1-30s)
    • result saying some variant of "still polling / in progress / waiting"

The earlier in the wait you notice this, the more orchestrator budget you save by taking over.

Solution

The instruction that causes this most often is a PROHIBITION the agent reads as a command

The brief in the section above at least asks for the polling. The commoner and more expensive case is a line you wrote to stop an agent doing something, which it reads as an instruction to stand and watch:

Read the full file on GitHub · 277 lines

Changes

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.

  1. 5d ago First seen · 277 lines · 341 tokens per session scan A 1274afa4af5b

Subscribe to this mod's changes

subagent-external-wait-orchestrator-takeover is a skill published in the GitHub repository wan-huiyan/agent-traffic-control (3 stars, last pushed 5d ago), licensed MIT. It adds 341 tokens to every session and 3,082 once invoked, about $0.0017 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 2026-09-05.

Related

Other skills, from other repositories

cloudflare-cron-triggers

Cloudflare Cron Triggers for scheduled Workers execution. Use for periodic tasks, scheduled jobs, or encountering handler not found, invalid cron expression, timezone errors.

secondsky/claude-skills · 38 tokens

cloudflare-nextjs

Deploy Next.js to Cloudflare Workers via the OpenNext adapter (@opennextjs/cloudflare). Use for SSR/ISR/SSG/App or Pages Router, getCloudflareContext, bindings (D1/R2/KV/AI/Hyperdrive), caching tiers, skew protection, multi-worker, custom worker, env vars, or worker…

secondsky/claude-skills · 89 tokens

cloudflare-workers-testing

Comprehensive testing guide for Cloudflare Workers using Vitest and @cloudflare/vitest-pool-workers. Use for test setup, binding mocks (D1/KV/R2/DO), integration tests, or encountering test failures, mock errors, coverage issues.

secondsky/claude-skills · 57 tokens

cloudflare-browser-rendering

Cloudflare Browser Rendering with Puppeteer/Playwright. Use for screenshots, PDFs, web scraping, or encountering rendering errors, timeout issues, memory exceeded.

secondsky/claude-skills · 37 tokens

cloudflare-queues

This skill should be used when the user asks to "set up Cloudflare Queues", "create a message queue", "implement queue consumer", "process background jobs", "configure queue retry logic", "publish messages to queue", "implement dead letter queue", or encountering "queue timeout", "message retry", "throughput…

secondsky/claude-skills · 78 tokens

cloudflare-workers-ci-cd

Complete CI/CD guide for Cloudflare Workers using GitHub Actions and GitLab CI. Use for automated testing, deployment pipelines, preview environments, secrets management, or encountering deployment failures, workflow errors, environment configuration issues.

secondsky/claude-skills · 50 tokens