NTM — Named Tmux Manager
Core capability: Turn
tmuxinto a structured, recoverable multi-agent workspace.
Read the repo first. If the target repository has
AGENTS.mdorREADME.md, read those before applying this skill. Repo-local instructions override generic NTM advice.
Interactive vs automation:
ntm dashboard,ntm palette,ntm web, and other TUI/web surfaces are for humans.- For machine-readable automation, prefer
--robot-*.- Non-interactive CLI commands such as
ntm send,ntm work triage,ntm attention list,ntm locks list,ntm pipeline status, andntm serveare fine when they are the clearest tool.
Coordination and isolation:
- Agent Mail reservations are the default coordination primitive.
--worktreesandntm worktrees ...are supported isolation tools when the repo policy allows them.- If a repo
AGENTS.mdprefers reservations-only or has worktree-specific rules, follow that repo.
Quick Start
# Install / sanity check
curl -fsSL "https://raw.githubusercontent.com/Dicklesworthstone/ntm/main/install.sh?$(date +%s)" | bash -s -- --easy-mode
ntm deps -v
# Create or resolve a project
ntm quick myproject --template=go
# Launch a mixed swarm
ntm spawn myproject --cc=2 --cod=1 --agy=1
# Dispatch work
ntm send myproject --cc "Map the auth layer and propose a refactor plan."
# Inspect the current work graph and system state
ntm work triage --format=markdown
ntm --robot-snapshot
Session Orchestration
Use these for day-to-day session lifecycle management:
ntm spawn myproject --cc=3 --cod=2 --agy=1
ntm spawn myproject --grok=1 --omp=1 --oc=1
ntm spawn myproject --label frontend --cc=2
ntm spawn myproject --label backend --cc=2 --worktrees
ntm add myproject --cc=1
ntm add myproject --label frontend --cod=1
ntm list
ntm status myproject
ntm view myproject
ntm zoom myproject 3
ntm attach myproject
ntm dashboard myproject
ntm palette myproject
ntm web
In ntm palette, target selection keys cover every built-in harness: 1-5 (All / Claude / Codex / Gemini / Antigravity), 7 Oh My Pi (omp), 8 Grok (grok), 9 OpenCode (oc), and 6 to pick individual agent panes.
Useful spawn patterns:
ntm spawn myproject --prompt "Read AGENTS.md and start on ready work"
ntm spawn myproject -r full-stack
ntm spawn myproject -t red-green
ntm spawn myproject --persona=architect --persona=implementer:2
ntm spawn myproject --stagger-mode=smart --cc=6 --cod=4
Stagger defaults can live in config so every spawn paces prompts (flags win):
[spawn]
stagger_mode = "fixed" # none | fixed | smart
stagger_delay = "90s" # 0-5m
Dispatch and Reusable Assets
High-leverage NTM usage is not just spawn plus send. The real power shows up when
you combine richer dispatch patterns with reusable session and prompt assets.
ntm send myproject --all "Checkpoint and summarize blockers."
ntm send myproject --pane=2 "Own the auth migration."
ntm send --project myproject "Sync to main and report conflicts."
ntm send myproject -c internal/auth/service.go "Review this subsystem"
ntm send myproject -t fix --var issue="nil pointer" --file internal/auth/service.go
ntm send myproject --route=affinity "Take the auth follow-up in internal/auth/service.go"
ntm send myproject --distribute --dist-strategy=dependency
ntm recipes list
ntm recipes show full-stack
ntm workflows list
ntm workflows show red-green
ntm template list
ntm template show refactor
ntm session-templates list
ntm session-templates show refactor
User-level and project-level assets both matter. NTM can resolve configuration from
~/.config/ntm/... and project-local .ntm/... trees, so check the repo before
assuming defaults.
Reasoning Ensembles
Multi-mode reasoning ensembles are graduated into default NTM builds for structured diagnosis, adversarial review, synthesis, run comparison, and finding provenance:
ntm modes list --tier core
ntm ensemble suggest "What security issues exist in the auth layer?" --json
ntm ensemble spawn myensemble --preset project-diagnosis --question "What are the main architectural risks?"
ntm ensemble status myensemble --format=json
ntm ensemble synthesize myensemble --format=json
ntm ensemble compare myensemble-v1 myensemble-v2 --format=json
ntm ensemble provenance --all --format=json
Work Intelligence
NTM is no longer just a pane launcher. It has first-class work selection and assignment:
ntm work triage
ntm work triage --by-track
ntm work alerts
ntm work search "JWT auth"
ntm work impact internal/api/auth.go
ntm work next
ntm work graph
ntm assign myproject --auto --strategy=dependency
ntm assign myproject --beads=br-123,br-124 --agent=codex
Use ntm work ... when you want NTM to wrap bv and present work in operator-friendly form.
Use raw bv --robot-* when you specifically want the graph engine's native robot output.
Coordination and Recovery
NTM now exposes the surrounding coordination stack directly:
ntm mail send myproject --all "Report blockers and current file focus."
ntm mail inbox myproject
ntm locks list myproject --all-agents
ntm locks renew myproject
ntm locks force-release myproject 42 --note "agent inactive"
ntm coordinator status myproject
ntm coordinator digest myproject
ntm coordinator conflicts myproject
ntm attention list --json
ntm attention ack 42 --reason "investigating pane_2"
ntm attention snooze 42 --until 30m --reason "waiting on build"
ntm attention pin 42 --reason "release blocker"
ntm attention dismiss 42 --reason "false alarm"
ntm checkpoint save myproject -m "before risky refactor"
ntm checkpoint list myproject
ntm checkpoint restore myproject
ntm timeline list
ntm timeline show <session-id>
ntm history search "authentication error"
ntm audit show myproject
ntm conflicts myproject
ntm resume myproject
ntm locks force-release is approval-gated by default (automation.force_release: approval): the first run files a durable approval request, a second operator grants it with ntm approve <id> (self-approval is rejected), and re-running the command consumes the approval and executes once. A solo operator can set ntm policy automation --force-release auto to allow unattended force-release.
Treat ntm checkpoint save as a routine cadence, not just a pre-disaster snapshot. Good points to checkpoint: once prompts are confirmed received after a spawn or restore, after an investigation isolates a root cause, before risky edits, after significant uncommitted work but before verification, after a green verification, and before a merge/cleanup/handoff. Cheap checkpoints make any later ntm checkpoint restore land on a known-good state.
Note that Agent Mail may run as an external MCP or service-manager process outside the tmux session. If Agent Mail and tmux appear to fail together, don't assume tmux took Agent Mail down — check the service manager, process/cgroup ancestry, and OOM/memory signals at the service boundary before relaunching workers.
Isolation options:
# Coordination-first
ntm locks list myproject
# Isolation-first when policy allows it
ntm spawn myproject --cc=3 --worktrees
ntm worktrees list
ntm worktrees merge claude_1
Safety and Approvals
NTM has built-in safety, policy, and approval surfaces. Use them instead of ad hoc shell habits:
ntm safety status
ntm safety check -- git reset --hard
ntm safety blocked --hours 24
ntm safety install # also registers the Claude hook in ~/.claude/settings.json
ntm policy show --all
ntm policy validate
ntm policy edit
ntm policy automation
ntm approve list
ntm approve show abc123
ntm approve abc123
ntm approve deny abc123 --reason "wrong target branch"
If the repo instructions require offloading builds or tests through another tool such as rch, obey the repo instructions.
Canonical Robot Mode
Start with these:
ntm --robot-help
ntm --robot-capabilities
ntm --robot-status
ntm --robot-snapshot
ntm --robot-plan
ntm --robot-dashboard
ntm --robot-markdown --compact
ntm --robot-terse
Common task-specific robot surfaces:
ntm --robot-spawn=myproject --spawn-cc=3 --spawn-prompt="Read AGENTS.md and start on ready work" --spawn-stagger-mode=fixed --spawn-stagger-delay=90s
ntm --robot-send=myproject --msg="Summarize blockers." --type=claude
ntm --robot-ack=myproject --timeout=30s
ntm --robot-tail=myproject --lines=50
ntm --robot-mail-check --mail-project=myproject --urgent-only
ntm --robot-cass-search="authentication error"
ntm --robot-beads-list --status=open
ntm --robot-bead-claim=br-123 --bead-assignee=agent1
ntm --robot-bead-close=br-123 --bead-close-reason="Completed"
ntm --robot-ensemble=myensemble
ntm --robot-ensemble-modes --tier=core
ntm --robot-ensemble-presets
ntm --robot-ensemble-suggest="What security issues exist?"
ntm --robot-ensemble-synthesize=myensemble --synth-force
ntm --robot-send=myproject --msg="Apply schema migration" --op-id=deploy-42
ntm --robot-action-status=deploy-42
ntm --robot-wait-request=deploy-42 --timeout=30s
ntm --robot-cancel-request=deploy-42
--spawn-prompt (or --spawn-prompt-file) waits for readiness, then reaches
each agent through robot send's dispatch path; the JSON reports the
stagger.schedule[] (per-agent delay_ms/scheduled_at) and
prompt_deliveries[] (per-agent prompt_sent/delivered_at). The same
--spawn-stagger-* flags pace --spawn-assign-work prompts.
Operator loop:
1. Bootstrap with --robot-snapshot
2. Tend with --robot-attention or --robot-wait
3. Act with --robot-send, ntm send, ntm assign, ntm locks, or ntm mail
4. Re-bootstrap with --robot-snapshot if the cursor expires
Prefer --robot-* when another agent or script needs structured output.
Serve API and Pipeline Surfaces
NTM also exposes the embedded web cockpit, local REST/SSE/WebSocket API, and durable workflow surfaces:
ntm web
ntm serve --port 7337
ntm openapi generate
ntm pipeline run .ntm/pipelines/review.yaml --session myproject
ntm pipeline status run-20241230-123456-abcd
ntm pipeline list
ntm pipeline resume run-20241230-123456-abcd
ntm pipeline cleanup --older=7d
ntm web mounts the embedded browser cockpit at http://127.0.0.1:7337 alongside the REST/SSE/WebSocket API and live OpenAPI 3.1 spec at http://127.0.0.1:7337/api/v1/openapi.json. Use ntm serve for headless local integrations, and --robot-* for single-shot agent control.
Project Resolution
ntm spawn needs a project directory that NTM can resolve.
ntm config get projects_base
ntm quick myproject --template=go
# Or point projects_base at an existing repo layout / create a symlink when needed
The session name usually matches the project directory name. Labels extend the session name as project--label.
Reference Index
Read these when you need deeper detail without bloating the main skill body:
| Topic | Reference |
|---|---|
| High-leverage command patterns, output capture, monitoring, reusable assets | COMMANDS.md |
| Attention feed, robot output formats, wait conditions, mail/cass/bead robot flows | ROBOT-MODE.md |
| Human dashboard, palette, keybindings, and TUI implementation notes | DASHBOARD.md |
Project resolution, projects_base, config paths, and project-local assets |
CONFIG.md |
Related Skills
agent-mailfor inboxes, contact handshakes, and file reservationsbrfor bead state changes and syncingbvfor graph-aware task prioritizationcassfor prior-session retrieval