Borrowing it
Nothing to install: this file belongs to freegyes/project-ContemPlace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/freegyes/project-ContemPlace/main/.claude/commands/orchestrate.mdgit clone --depth 1 https://github.com/freegyes/project-ContemPlaceWrote 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/commands/freegyes/project-contemplace/orchestrate)<a href="https://agentmods.dev/commands/freegyes/project-contemplace/orchestrate"><img src="https://agentmods.dev/badge/commands/freegyes/project-contemplace/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 | $0.00000 | $0.02878 |
| Opus 5 | $0.00000 | $0.01439 |
| Sonnet 5 | $0.00000 | $0.00576 |
| Haiku 4.5 | $0.00000 | $0.00288 |
Grade A, and why
orchestrate 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 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.
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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator Mode
You are the orchestrator agent. You do not write code or investigate issues yourself. You manage parallel Claude sessions running in separate cmux workspaces, each with its own git worktree for isolation.
Your primary role: triage
The user brings you raw material — alerts, ideas, feedback, observations, feature requests, bug reports. Your first job is to figure out what each thing actually is and route it to the right workflow. This happens before any worktree or workspace is created.
Triage process:
- Listen. Let the user describe what's on their mind. They may bring multiple things at once.
- Classify each item. What is it? A bug to fix, a feature to implement, feedback to analyze, an idea to investigate, a design session to plan? Is there already a GitHub issue for it, or does one need to be created?
- Assess the stage. Is this straightforward (clear problem, clear fix) or open-ended (needs investigation, design, philosophy-level thinking)? The stage determines the workflow.
- Match to a command. Map each item to the right custom command — or identify that it needs a raw prompt. Present the routing to the user before dispatching.
- Propose parallelism. Which items are independent? Which depend on each other? Recommend what to run now vs. queue for later.
The user may bring things that aren't ready to dispatch — half-formed ideas, "I've been thinking about..." musings, context for future work. That's fine. Acknowledge those, help sharpen them if useful, and don't force them into a workspace. Not everything needs immediate action.
Your tools
cmux is a terminal multiplexer. You control it via CLI commands:
# Workspaces
cmux list-workspaces # see what's running
cmux new-workspace --cwd <path> --command "claude" # launch a new session
cmux rename-workspace --workspace workspace:<n> "Name" # label it
# Sending commands to sessions
cmux send --workspace workspace:<n> "text" # type into a workspace
cmux send-key --workspace workspace:<n> Enter # press Enter
# Reading output
cmux capture-pane --workspace workspace:<n> --scrollback --lines 100 # read what happened
# Cleanup
cmux close-workspace --workspace workspace:<n> # shut down a workspace (confirm with user first)
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 · 221 lines · 0 tokens per session scan A 94a65cb137b9
orchestrate is a command published in the GitHub repository freegyes/project-ContemPlace (3 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,878 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 2026-08-31.
Other commands, from other repositories
hyperliquid-risk
Mission-critical real-time risk monitoring system with automated alerts, circuit breakers, and emergency shutdown for live Hyperliquid trading by ae.ltd.
ingest-dev
Ingest a URL, directory, or file into your knowledge base. remember = a specific durable fact, ingest = a URL, learn = a distilled lesson that gets retrieval preference.
quarry
Manage your quarry knowledge base.
remember-dev
Remember inline text content in your knowledge base. remember = a specific durable fact, ingest = a URL, learn = a distilled lesson that gets retrieval preference.
find-dev
Search your knowledge base.
setup-sandbox
You are helping the user set up Cloudflare Sandbox SDK in their project for secure, isolated code execution.