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 skills/urmzd/dotfiles/orchestrate-agentsnpx skills add urmzd/dotfiles --skill orchestrate-agentsgit clone --depth 1 https://github.com/urmzd/dotfilesWrote 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/urmzd/dotfiles/orchestrate-agents)<a href="https://agentmods.dev/skills/urmzd/dotfiles/orchestrate-agents"><img src="https://agentmods.dev/badge/skills/urmzd/dotfiles/orchestrate-agents.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 | $0.00083 | $0.03246 |
| Opus 5 | $0.00042 | $0.01623 |
| Sonnet 5 | $0.00017 | $0.00649 |
| Haiku 4.5 | $0.00008 | $0.00325 |
Grade A, and why
orchestrate-agents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate Agents
Requires tmux and at least one agent CLI (claude, codex, copilot, or agy). Optional: agentspec (session transcripts), osascript (macOS notifications) or notify-send (Linux notifications). Run
"$fleet" doctorto see which are present; a missing CLI just drops out of the preference order.
Run several interactive agent CLIs at once inside one tmux session, supervise them, and alert the user the moment one is blocked, errored, idle, or done. You are the orchestrator: careful, never silently let an agent stall. Orchestrate what exists before creating anything: survey running tmux state first, adopt and extend existing sessions/windows/panes, and spawn new ones only when nothing suitable is already running (or the user asks to extend).
scripts/fleet.sh owns the fragile tmux plumbing (spawn, send, capture, idle
detection, alerting). You decide what to spawn and when to ping.
Set the helper path once, then drive it:
fleet="${CLAUDE_SKILL_DIR:-$HOME/.agents/skills}/orchestrate-agents/scripts/fleet.sh" # shared store; stable across tools
"$fleet" doctor # confirm tmux + which agent CLIs + agentspec + notifier are present
If doctor shows a CLI missing, it just drops out of the preference order.
Model
- Fleet = one tmux session. One per orchestration run.
- Window = a workstream group (per feature, per repo, per phase).
- Pane = one agent CLI. Reference agents by the pane id (
%7) the helper returns, never by name (the user's shell hook may auto-rename windows; pane ids and@fleet_*tags are immune). - Guardian = a
guardiansubagent dedicated to one pane. Spawned at the same moment the pane joins the fleet (atspawn, or atadoptfor existing panes). The orchestrator never readscapturedirectly during the supervision loop; it reads the guardian's contract lines instead.
Tool preference when a workstream does not pin one: claude, codex first, then copilot, then agy. See references/agent-clis.md for each CLI's launch, headless, auto-approve, and resume flags.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 264 lines · 83 tokens per session scan A 725431a86b4e
orchestrate-agents is a skill published in the GitHub repository urmzd/dotfiles (3 stars, last pushed 21d ago), licensed Apache-2.0. It adds 83 tokens to every session and 3,246 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
coding
Principles for writing and designing code, covering API and abstraction design, naming, comment discipline, and standards of evidence for claims about code behavior. Use whenever the task is to write or modify code, design an API or software architecture, or review code.
review-code
Standalone code review for any scope — PR number, branch, file paths, or current changes. Synthesizes intent, runs 10 parallel specialized agents, and presents actionable findings with a verdict. For PR scope, optionally posts the review to GitHub with inline comments.
review-prs
Fetch and present a prioritized summary of all PRs awaiting the current user's review across the relevant projects and provide an interactive workflow helping the user phrase and post inline review comments and overall review decisions.
review-converge
Autonomously review and fix the current branch or specified scope in iterative rounds until clean, leaving all changes in the working tree. Escalates only genuine design decisions. Ends with a transparent report of every round, every fix, and anything it couldn't resolve — persisted to .outputs/.
review-pr-comments-converge
Fetch PR review comments, validate each against the actual code, auto-fix obvious issues, and escalate genuine design decisions. Leaves all changes in the working tree. Use when you want to action reviewer feedback autonomously.
write-ticket-description
Voice guide for writing issue/ticket/task/epic descriptions. Use this skill for ALL issue creation — GitHub issues, Jira tasks, Monday tasks, Linear tasks, and epics. Contains section structure, voice rules, and anti-patterns. Never write ticket descriptions without invoking this skill first.