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 commands/disler/learning-cmux-with-agents/primegit clone --depth 1 https://github.com/disler/learning-cmux-with-agentsWrote 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/disler/learning-cmux-with-agents/prime)<a href="https://agentmods.dev/commands/disler/learning-cmux-with-agents/prime"><img src="https://agentmods.dev/badge/commands/disler/learning-cmux-with-agents/prime.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 | $0.00031 | $0.00708 |
| Opus 5 | $0.00015 | $0.00354 |
| Sonnet 5 | $0.00006 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
prime 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 — 21 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Catch up on this codebase. It is a study of cmux — a native macOS terminal (built on Ghostty) for running many AI coding agents at once — and a hands-on proof, via 31 natural-language prompts, that one primary agent can stand up, prompt, watch, customize, and tear down a whole fleet of other agents and terminals through cmux's CLI and Unix socket. We are exploring cmux's capabilities and confirming it satisfies three concrete use cases (it does):
- Agentic access to every terminal window — the orchestrator can see and script every surface (
send/read-screen/close-surface). → Tiers 1–5. - Customizable UI panes to distinguish leads from workers in a 3-tier agent team — per-workspace color/pill/icon (prompt 26) + per-pane identity (prompt 31).
- Reusable session files that boot new teams at the speed of agents — declarative layouts-as-code (prompt 09) + crash-proof resume (prompt 24).
Workflow
- List the tracked files to see the shape of the repo:
git ls-files 2>/dev/null || find . -type f -not -path '*/.git/*' -not -path '*/legacy/*' | sort. - Read
README.md— the thesis, the "## The Problem — Three Things I Need From a Fleet Terminal" section (the three proofs), the mental model (Window ⊃ Workspace ⊃ Pane ⊃ Surface), the control loop (send·send-key·read-screen·close-surface), and the tier breakdown. - Read
guide/index.html— the simplified single-page visual guide: hero + concept sections + the full tier library with copy-able prompts. This is the fastest high-level map of every capability. - Skim the prompt library in
prompts/(01–31+PATTERNS-read-and-notify.md). Read at least one per group to learn the file shape — each has a🗣 The prompt(plain English), a🧠 answer key(the exactcmuxverbs it compiles to), and✅ Done whencriteria. Groups: 01–05 Foundations · 06–10 One Agent · 11–16 Fleet · 17–20 Browser · 21–25 Scale · 26–31 Customization. - Skim
ai_docs/cmux-skills/— the 9 agent-facing skills (cmux,cmux-workspace,cmux-browser,cmux-customization,cmux-settings,cmux-keyboard-shortcuts,cmux-custom-sidebar,cmux-diagnostics,cmux-markdown) are the real verb surface that powers the prompts. - Summarize your understanding of the project: what cmux is, the thesis, the five-box mental model, the four-verb control loop, the three use cases we're proving, where each proof lives, and how the
prompts/files are structured.
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 · 21 lines · 31 tokens per session scan A a5f5433de8ac
prime is a command published in the GitHub repository disler/learning-cmux-with-agents (109 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 708 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.