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 skills/amirlehmam/wmux/orchestratenpx skills add amirlehmam/wmux --skill orchestrategit clone --depth 1 https://github.com/amirlehmam/wmuxWrote 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/amirlehmam/wmux/orchestrate)<a href="https://agentmods.dev/skills/amirlehmam/wmux/orchestrate"><img src="https://agentmods.dev/badge/skills/amirlehmam/wmux/orchestrate.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 5.1 | $0.00039 | $0.05884 |
| Opus 5 | $0.00019 | $0.02942 |
| Sonnet 5 | $0.00008 | $0.01177 |
| Haiku 4.5 | $0.00004 | $0.00588 |
Grade B, and why
orchestrate scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
PLUGIN_ROOT=$(find "$HOME/.claude/plugins/cache/wmux-orchestrator" -name "plugin.json" -path "*/.claude-plugin/*" 2>/dev/null | sort -V | tail -1 | sed 's|/.claude-plugin/plugin.json||') How it starts
The opening of the file, as written. The whole thing — 524 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wmux Orchestration Skill
You are the orchestrator. Your job is to decompose the user's task into parallel subtasks, create a wave-based execution plan, and launch Claude Code agents to execute it.
Phase 0: Resolve Plugin Root
CLAUDE_PLUGIN_ROOT is set by Claude Code only inside hook execution, NOT in the main session's shell environment. You MUST resolve the plugin root path before running any scripts.
Run this to find and export the plugin root:
PLUGIN_ROOT=$(find "$HOME/.claude/plugins/cache/wmux-orchestrator" -name "plugin.json" -path "*/.claude-plugin/*" 2>/dev/null | sort -V | tail -1 | sed 's|/.claude-plugin/plugin.json||')
echo "PLUGIN_ROOT=$PLUGIN_ROOT"
ls "$PLUGIN_ROOT/scripts/" | head -5
If the find returns empty, the plugin is not installed. Tell the user:
"wmux-orchestrator plugin not found. Install it with:
claude plugins install wmux-orchestrator@wmux-orchestrator"
Store PLUGIN_ROOT and use it for ALL subsequent bash commands in this orchestration. Every script reference below uses $PLUGIN_ROOT — you must prefix every bash command that references plugin scripts with the same export or pass the resolved path directly.
Phase 1: Detect wmux
Run the detection script:
bash "$PLUGIN_ROOT/scripts/detect-wmux.sh"
Store the result as WMUX_MODE:
- If output is
"available"→WMUX_MODE=wmux— agents spawn in visible terminal panes viawmux agent spawn - If output is
"unavailable"→WMUX_MODE=degraded— agents spawn as invisible Claude Code subagents via the Agent tool
This decision is binding for the entire orchestration. Do not switch modes mid-orchestration.
If degraded, log to the user:
"wmux not detected. Running in degraded mode — agents will use Claude Code's native subagent system. Install wmux for the full multi-pane experience: https://wmux.org"
If wmux mode, log to the user:
"wmux detected. Agents will spawn in visible terminal panes."
Phase 2: Analyze the Codebase
Before decomposing, understand what the task involves:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 524 lines · 39 tokens per session scan B ccc20f0d2d9f
orchestrate is a skill published in the GitHub repository amirlehmam/wmux (366 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 5,884 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…