agent-orchestration

agent-orchestration is a skill for Claude Code, Codex from deepgram/wsh. It costs 78 tokens per session (2,317 once invoked), scanned C, original, ISC.

A skill for launching and coordinating other AI coding agents through their terminal interfaces. It can work with agents such as Claude Code, Aider, and Codex.

In plain words
What is it for?
It is for starting agents, sending them instructions, handling their terminal interaction, and reviewing their progress.
Why use it?
It helps divide work across multiple agent sessions and manage their tasks and approval prompts from one workflow.

Skill for Claude CodeCodex

Part of the wsh plugin — 12 skills shipped together

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/deepgram/wsh/agent-orchestration
Any agent
npx skills add deepgram/wsh --skill agent-orchestration
Clone the repo
git clone --depth 1 https://github.com/deepgram/wsh

Made for: Claude Code, Codex.

Or install wsh, the plugin that ships this one along with the rest of its 12 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 agent-orchestration

README.md
[![agentmods](https://agentmods.dev/badge/skills/deepgram/wsh/agent-orchestration.svg)](https://agentmods.dev/skills/deepgram/wsh/agent-orchestration)
Your own site
<a href="https://agentmods.dev/skills/deepgram/wsh/agent-orchestration"><img src="https://agentmods.dev/badge/skills/deepgram/wsh/agent-orchestration.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,317 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00078 $0.02317
Opus 5 $0.00039 $0.01158
Sonnet 5 $0.00016 $0.00463
Haiku 4.5 $0.00008 $0.00232

Measured 4d ago against content hash 1dc54145d5ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

agent-orchestration scanned grade C with 2 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

# See: "Run command: rm -rf /tmp/build"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> 2. **If you do NOT have `wsh_*` tools**: you are in HTTP/curl fallback mode.
skills/agent-orchestration/SKILL.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IMPORTANT: EXECUTION CONTEXT This skill describes what to do — domain patterns and decision-making. It does NOT describe how to call the API.

  1. If you have wsh_* tools (check your toolkit for wsh_send_input, wsh_get_screen, etc.): use them directly. Operation names in this skill generally map to tool names (e.g., "send input" → wsh_send_input). When in doubt, list your available wsh_* tools.
  2. If you do NOT have wsh_* tools: you are in HTTP/curl fallback mode. DO NOT GUESS endpoints or CLI subcommands. Load the full API reference first: search your workspace for skills/core/ and read SKILL.md. It contains every endpoint with working curl examples and a bootstrap sequence.
  3. Quick bootstrap: curl -sf --unix-socket ${XDG_RUNTIME_DIR:-/tmp}/wsh/default.http.sock http://localhost/health — if that fails: wsh server -L agent-$$ --ephemeral & and retry.

wsh:agent-orchestration — Driving AI Agents

You can use wsh to launch and drive other AI agents — Claude Code, Aider, Codex, or any AI tool with a terminal interface. This is not science fiction. You spawn the agent in a wsh session, feed it tasks, handle its approval prompts, and review its output. You become a manager of AI workers.

Why?

  • Parallelism. You can run 5 Claude Code sessions simultaneously, each working on a different task.
  • Delegation. Break a large project into subtasks and assign each to an agent session.
  • Specialization. Different agents have different strengths. Orchestrate the right tool for each job.
  • Automation. Unattended workflows — an agent that spawns agents, reviews their work, and merges the results.

Launching an Agent

Create a session with the agent as its command:

create session "agent-auth" with command: claude --print "Implement user auth in src/auth.rs"

Or start a shell and launch the agent interactively:

create session "agent-auth"
send: claude
wait for idle
read screen — verify Claude Code has started
send: Implement user authentication in src/auth.rs\n

Read the full file on GitHub · 293 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. 4d ago First seen · 293 lines · 78 tokens per session scan C 1dc54145d5ef

Subscribe to this mod's changes

agent-orchestration is a skill published in the GitHub repository deepgram/wsh (5 stars, last pushed 3mo ago), licensed ISC. It adds 78 tokens to every session and 2,317 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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