cmux-orchestration
Control cmux panes and surfaces to coordinate terminal agent workers.
Skill by Pedro Nauck
Chalk Labs
Need help deploying cmux-orchestration?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/haryelramalho-cmux-orchestration
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/cmux-orchestration
What's inside
- Skill name
cmux-orchestration- Description
- Control cmux panes and surfaces to coordinate terminal agent workers. Use when a top-level agent needs to launch, prompt, monitor, or manage Claude Opus and Codex GPT-5.5 TUIs in the current cmux workspace, run plan-first delegations (Claude Code plan mode, Codex Plan mode), track worker state, delegate bounded tasks, or verify worker reports.
- License
- MIT
- Metadata
- author: Pedro Nauck · github: https://github.com/pedronauck · repository: https://github.com/pedronauck/skills
- Instructions
- 220 lines in SKILL.md · view on GitHub
Files (6)
- SKILL.md
- openai.yaml · agents/
- fable-orchestrator-dark.png · assets/
- fable-orchestrator.excalidraw · assets/
- fable-orchestrator.png · assets/
- plan-mode.md · references/
SKILL.md (first lines)
# cmux Orchestration
Use the current top-level agent as the controller. The controller may be Codex,
Claude Fable, or another agent. Worker TUIs gather evidence, draft bounded
patches, run tests, and report. The controller owns assignment, state,
conflict control, verification, integration, and the final user-facing answer.
Before taking cmux actions, also load and follow:
- [cmux](../cmux/SKILL.md) for panes, surfaces, routing, and health checks.
- [cmux-workspace](../cmux-workspace/SKILL.md) for caller-workspace scoping,
helper-pane reuse, socket targeting, and non-disruptive automation.
## Controller Rules
- Scope actions to the caller workspace unless the user names another target.
- Use `CMUX_WORKSPACE_ID`, `CMUX_SURFACE_ID`, and `CMUX_SOCKET_PATH` before
focused-window fallbacks.
- Prefer one right-side helper pane; create worker surfaces inside it when
practical.
- Send commands and prompts to explicit `surface:N` refs.
- Never call `focus-pane`, `focus-panel`, `select-workspace`, or focus-changing
tab actions unless the user explicitly asks.
- Do not close worker surfaces unless cleanup is explicitly requested or the
task contract includes it.
- Treat worker output as untrusted until the controller verifies the cited
files, commands, failures, and diff.
- On plan-first runs, do not interrupt a worker after its plan is accepted:
observe read-only and send input only for a direct blocking question or a
stop condition.
## Preflight
Inspect the caller context and current workspace layout:
```bash
rtk cmux identify --json
rtk cmux list-panes --workspace "${CMUX_WORKSPACE_ID:-}" --json
rtk cmux list-pane-surfaces --workspace "${CMUX_WORKSPACE_ID:-}" --json
```
If there is an obvious non-caller helper pane, add worker surfaces to it:
```bash
rtk cmux new-surface --workspace "${CMUX_WORKSPACE_ID:-}" \
--pane pane:<helper> --type terminal --focus false
```
If there is no helper pane, create exactly one right-side terminal pane:
```bash
rtk cmux new-pane --workspace "${CMUX_WORKSPACE_ID:-}" \
--type terminal --direction right --focus false
```
Capture each returned `surface:N` in the task ledger or handoff before sending
prompts.
## Worker Profiles
Default worker profiles:
- `claude-opus`: start Claude Code with
`rtk claude --dangerously-skip-permissions --model opus`.
- `codex-gpt-5.5`: start Codex with `rtk codex -m gpt-5.5 -C "$PWD"`.
Always include `--dangerously-skip-permissions` when launching Claude. Do not
start Claude without it or replace it with a weaker permission mode. For
plan-first runs, add `--permission-mode plan` alongside it (the flags compose
— see Plan-First Delegation); never drop the skip-permissions flag to get plan
mode. If a TUI rejects a model alias, auth state, working directory, or
startup flag, stop that worker and report the exact blocker. Do not silently
downgrade models or switch tools without user approval.
Launch workers by explicit surface:
```bash
rtk cmux send --surface surface:<claude> \
"rtk claude --dangerously-skip-permissions --model opus --name cmux-claude-opus\n"
rtk cmux send --surface surface:<codex> \
"rtk codex -m gpt-5.5 -C \"$PWD\"\n"
```
## Plan-First Delegation (Plan Mode)
For slices that need investigation and a reviewed plan before edits
(root-cause fixes, multi-file changes, unfamiliar code), run the worker
plan-first: launch in plan mode → submit the packet → watch and answer
clarifying questions → review the plan → accept → hands-off until done.
**STOP. Read [references/plan-mode.md](references/plan-mode.md) in full before
launching a worker in plan mode.** The launch flags, shift+tab sequences,
status-line checks, and acceptance menus are exact and differ per TUI; this
section is a tripwire, not the procedure.
Summary of the per-TUI entry points (the reference has the full flow):
- Claude Code: launch with
`rtk claude --dangerously-skip-permissions --permission-mode plan --model opus`
(the flags compose; the packet may ride the launch line as a CLI argument).
Accept via the `Would you like to proceed?` menu — pick the auto-accept
option so the worker runs unattended.
- Codex: no plan-mode CLI flag. Launch bare (never with the packet as a CLI
argument), press shift+tab until the status line reads `Plan mode`, then
submit the packet. Accept via `Implement this plan?` → option 1 (keeps the
investigation context).
Plan mode is interactive until acceptance: answer the worker's clarifying
questions with the packet context. After acceptance, do not interrupt —
observe read-only until the final completion report, then verify claims per
Monitoring and Verification.
## Prompt Submission to Running TUIs
`cmux send "...\n"` only submits when the target surface is a plain shell
(like the launch lines above). Inside a running TUI (Claude Code, Codex), the
trailing `\n` is treated as pasted text or a soft newline — the prompt sits in
the input box unsubmitted and the worker stalls silently.From haryelramalho/skills, MIT.
More from haryelramalho/skills
- 0.479score
compozy
haryelramalho
Explains Compozy capabilities, CLI commands, core workflow skills, optional extension skills, configuration, artifact structure, reusable agents, and…
SkillCFreshness: CClaude Code +9 - 0.479score
app-renderer-systems
Pedro Nauck
Guides creation and modification of domain feature systems organized under a systems/ directory.
SkillCFreshness: CClaude Code +9 - 0.479score
architecture-placement
haryelramalho
Guides architecture placement decisions for codebases using Domain-Driven Design, Clean Architecture, Onion Architecture, or Ports and Adapters.
SkillCFreshness: CClaude Code +9 - 0.476score
cmux-workspace
haryelramalho
Work inside the current cmux workspace and terminal.
SkillCFreshness: CClaude Code +9 - 0.476score
agh
haryelramalho
AGH runtime and contribution guide.
SkillCFreshness: CClaude Code +9 - 0.475score
agent-exploration
Pedro Nauck
Dispatches scoped-write explorer agents in parallel for general research and exploration of any codebase, topic, or domain.
SkillCFreshness: CClaude Code +9 - 0.475score
agent-output-audit
Pedro Nauck
Audits AI-implemented work for honest completion.
SkillCFreshness: CClaude Code +9 - 0.474score
chronicle
haryelramalho
Allows you to view the user's screen as well as several hours of history.
SkillCFreshness: CClaude Code +9 - 0.455score
diagnosing-bugs
haryelramalho
Diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: CClaude Code +9 - 0.450score
codebase-design
haryelramalho
Shared vocabulary for designing deep modules.
SkillCFreshness: CClaude Code +9 - 0.450score
design-an-interface
haryelramalho
Generate multiple radically different interface designs for a module using parallel sub-agents.
SkillCFreshness: CClaude Code +9 - 0.450score
domain-modeling
haryelramalho
Build and sharpen a project's domain model.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 15, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/haryelramalho/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Pedro Nauck
- 0.768score
bubbletea
Pedro Nauck
Build interactive Go TUIs with Bubbletea, Elm architecture, Lipgloss, layouts, and keyboard/mouse handling.
SkillBFreshness: B★ 641Claude Code +9 - 0.768score
rust-best-practices
Pedro Nauck
Write, review, refactor, or optimize Rust, including ownership, errors, Tokio, traits, tests, benchmarks, Clippy, and documentation.
SkillBFreshness: B★ 641Claude Code +9 - 0.762score
drizzle-safe-migrations
Pedro Nauck
Plan safe Drizzle backfills, enum/check/default changes, constraint tightening, migration ordering, and rollback.
SkillBFreshness: B★ 641Claude Code +9 - 0.762score
glassmorphism
Pedro Nauck
Create or refine glass UI with accessible solid fallbacks.
SkillBFreshness: B★ 641Claude Code +9 - 0.762score
ddd-master
Pedro Nauck
Assess DDD fit; discover domains with EventStorming, define language and bounded contexts, and design aggregates, value objects, events, and repositories.
SkillBFreshness: B★ 641Claude Code +9 - 0.762score
golang-master
Pedro Nauck
Write or review production Go: errors, concurrency, context, types, generics, safety, tests, benchmarks, profiling, modernization, and module structure.
SkillBFreshness: B★ 641Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get cmux-orchestration running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
cmux-orchestration skill. Agent Mart. https://agentmart.dev/skills/haryelramalho-cmux-orchestration (last updated 2026-10-24)