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 skills add ShreyPaharia/octomux --skill add-agentgit clone --depth 1 https://github.com/ShreyPaharia/octomuxWrote 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/shreypaharia/octomux/add-agent)<a href="https://agentmods.dev/skills/shreypaharia/octomux/add-agent"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/add-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shreypaharia/octomux/add-agent"><img src="https://agentmods.dev/badge/skills/shreypaharia/octomux/add-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.01105 |
| Opus 5 | $0.00018 | $0.00553 |
| Sonnet 5 | $0.00007 | $0.00221 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
add-agent 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 11d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add an agent to an octomux task
Attach a new Claude Code agent to an existing running task. The new agent is a fresh tmux window inside the task's tmux session, sharing the task's worktree/cwd. Each task can hold multiple agents working in parallel in the same worktree.
Distinction from send-agent-message
add-agent— creates a NEW agent (new tmux window, new Claude Code process) attached to an existing task. Use this to spin up an additional helper agent (e.g. a reviewer) alongside the original agent.send-agent-message— sends a message to an ALREADY-RUNNING agent via tmuxsend-keys. Use this to nudge or redirect an agent that is already working.
If you want another voice in the task, use add-agent. If you want to talk to the voice already there, use send-agent-message.
When to use
- Adding a reviewer / QA agent alongside an implementing agent
- Spawning an additional helper to work on a subtask in the same worktree
- Continuing an interrupted task with a fresh prompt without losing the original context in the running agent
Steps
-
Identify the task:
- If the user provides a task ID, use it directly
- Otherwise look it up. Prefer the MCP tool when available (you're in the orchestrator); otherwise fall back to the CLI:
- MCP:
mcp__octomux__list_tasks() - CLI fallback:
octomux list-tasks --json
- MCP:
- The task must be in
runningstatus —add-agentwill fail otherwise
-
Craft a focused initial prompt for the new agent. Keep it specific: the new agent lands in the same worktree but knows nothing about what the first agent has been doing.
-
Add the agent:
Prefer the MCP tool when available (you're in the orchestrator); otherwise fall back to the CLI.
MCP (preferred):
mcp__octomux__add_agent({ task_id: '<task-id>', prompt: '<initial prompt for the new agent>', label: '<optional label>', // optional — defaults to server-assigned "Agent N" model: '<optional model id>', // optional — e.g. "claude-opus-4-8" })
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.
- 11d ago First seen · 108 lines · 37 tokens per session scan A fb74ea5b1668
add-agent is a skill published in the GitHub repository ShreyPaharia/octomux (22 stars, last pushed 10d ago), licensed MIT. It adds 37 tokens to every session and 1,105 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 skills, from other repositories
muster
Coordinate with other coding-agent sessions — any machine, any vendor — on this repo via the muster CLI. Use when the user says /muster, asks to join or check a fleet, mentions muster, or wants to coordinate work with other sessions/machines on this repo.
release
Cut and publish a full stable NAC release after main, release-PR, and publication CI pass. Use when a maintainer asks for a stable version bump, tag, or GitHub Release. Never use for release candidates; NAC RC releases are automated.
triage
Triage a GitHub repository's open issues by finding exact duplicates, rejecting evidenceably off-base requests, requesting concrete clarification, applying only existing labels, and opening a linked root-cause issue when multiple reports share one underlying invariant failure. Use when a maintainer asks to triage…
bat-cat
A cat clone with syntax highlighting, line numbers, and Git integration - a modern replacement for cat.
conventional-commits
Format commit messages using the Conventional Commits specification. Use when creating commits, writing commit messages, or when the user mentions commits, git commits, or commit messages. Ensures commits follow the standard format for automated tooling, changelog generation, and semantic versioning.
commit-analyzer
Analyze git commit frequency, categories, and timing patterns to diagnose autonomous agent activity and operational health.