external-team-lead

external-team-lead is a skill for Claude Code, Codex from TentacleOpera/switchboard. It costs 0 tokens per session (1,797 once invoked), scanned A, original, MIT.

A workflow for an external agent to lead terminal-based worker agents through Switchboard, a local service for coordinating them. It uses files for team instructions and reports, and Git to check completed work.

In plain words
What is it for?
Dispatching work to terminal agents, reading their reports, and checking their code changes.
Why use it?
It defines how a lead agent can coordinate workers without its own terminal window and verify their changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

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.

agentmods
npx agentmods add skills/tentacleopera/switchboard/external-team-lead
Any agent
npx skills add TentacleOpera/switchboard --skill external-team-lead
Clone the repo
git clone --depth 1 https://github.com/TentacleOpera/switchboard

Made for: Claude Code, Codex.

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 external-team-lead

README.md
[![agentmods](https://agentmods.dev/badge/skills/tentacleopera/switchboard/external-team-lead.svg)](https://agentmods.dev/skills/tentacleopera/switchboard/external-team-lead)
Your own site
<a href="https://agentmods.dev/skills/tentacleopera/switchboard/external-team-lead"><img src="https://agentmods.dev/badge/skills/tentacleopera/switchboard/external-team-lead.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,797 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01797
Opus 5 $0.00000 $0.00898
Sonnet 5 $0.00000 $0.00359
Haiku 4.5 $0.00000 $0.00180

Measured yesterday against content hash 7af4abebe012, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

external-team-lead 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 yesterday.

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.

.agents/skills/external-team-lead/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: External Team Lead Mode

This skill defines how a non-terminal external agent (Antigravity, Cursor, Zed, IDE chat, or any chat agent with localhost CLI and filesystem access) operates as the lead of a team of terminal worker agents in Switchboard.


1. Core Operating Concept

In External-Headed Team Mode:

  • You (the external agent) are the Team Lead. You have no terminal window in the fleet; you control the team entirely via HTTP calls to Switchboard's LocalApiServer and file reads/writes in the workspace.
  • Workers are terminal agents. They execute subtasks in terminal ptys, code in worktrees/branches, and report completion by writing markdown report files to .switchboard/teams/<teamId>/reports/.
  • State and instructions persist on disk. Your instructions, roster, and active feature are stored in .switchboard/teams/<teamId>/head-prompt.md.
  • Verification is empirical. You verify code changes with git, not by trusting self-reports.
  • Plan files are the source of truth. You read them, dispatch based on them, and review against them. You never rewrite, edit, or restructure plan content. Your only write to a plan file is the completion-report append (if you are also coding), never a rewrite of the plan's content sections.
  • Lead-Paced Pipeline. When your current feature passes review, you pull the next staged card with POST /kanban/queue/next.

2. API Access

All interactions with Switchboard go through the switchboard CLI (switchboard api <METHOD> <path> [jsonBody]). Verify Switchboard is running:

switchboard api GET /health

3. Team Initialization

To create an external-headed team:

switchboard api POST /teams/create-external '{
  "template": "Coding",
  "headName": "<your-agent-name>",
  "featureId": "<optional-feature-id>"
}'

Response returns:

{
  "success": true,
  "teamId": "team_<your-agent-name>",
  "workers": [ ... ],
  "headPromptFile": ".switchboard/teams/team_<your-agent-name>/head-prompt.md",
  "reportsDir": ".switchboard/teams/team_<your-agent-name>/reports"
}

Read the full file on GitHub · 160 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. yesterday Changed · -7 lines 7af4abebe012
  2. 6d ago First seen · 167 lines · 0 tokens per session scan A 0b9b88dd8c53

Subscribe to this mod's changes

external-team-lead is a skill published in the GitHub repository TentacleOpera/switchboard (214 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,797 tokens. 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens