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 ngocsangyem/MeowKit --skill orchestrategit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/orchestrate)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/orchestrate"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/orchestrate/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/ngocsangyem/meowkit/orchestrate"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/orchestrate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00133 | $0.03699 |
| Opus 5 | $0.00067 | $0.01850 |
| Sonnet 5 | $0.00027 | $0.00740 |
| Haiku 4.5 | $0.00013 | $0.00370 |
Grade A, and why
mk:orchestrate 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 9d 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate
Coordinate headless coding-agent jobs and in-session toolkit subagents through a staged, captured, resumable workflow. This is a skill-level coordinator — not a daemon, scheduler, or new runtime. It coordinates runtimes that already exist on the machine.
Runtime and model catalogs drift constantly. Resolve every route from live execution-time evidence. Never treat a runtime, provider, model, alias, flag, or agent seen in this file or an older report as currently available.
Inputs
/mk:orchestrate "research three implementation options and compare them"
/mk:orchestrate "compare the auth options" --internal
/mk:orchestrate tasks/plans/orchestrate-jobs.yaml
/mk:orchestrate tasks/plans/orchestrate-jobs.yaml --yes
/mk:orchestrate --resume tasks/reports/orchestrate-<timestamp>
Use a YAML job spec for repeatable runs. For a free-form request, create a
temporary spec at tasks/reports/orchestrate-<timestamp>/jobs.yaml before
dispatch.
--internal is a routing preference, not a hard mode. It asks the selection
policy to consider in-session subagents first for jobs without an explicit
runtime:. A job that needs a separately selectable model, stronger enforced
isolation, or a control the current harness lacks may use a live-verified CLI
fallback. --yes pre-approves the exact destructive scope described in the spec.
Never override an explicit runtime, model, or agent pin silently.
Authority Map
Each durable contract lives in exactly one reference. Do not copy runtime or model catalogs into this file. When references disagree, STOP and report the contract mismatch.
| Reference | Owns |
|---|---|
| model-routing.md | Sole route-selection authority: capability/risk tiers, task defaults, internal selection, fallback qualification, model-family independence |
| runtime-matrix.md | Live candidate discovery, probing, command verification, OS evidence, <run-dir>/runtimes.json |
| harness-profiles.md | Evidence schema for permissions, isolation, capture, budgets, enablement |
| internal-routing.md | In-session subagent dispatch, capture, timeout, resume mechanics |
| job-spec.md | YAML schema and execution-state contract |
What ships with it
5 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.
- 9d ago First seen · 358 lines · 133 tokens per session scan A 9a6ff0a4b101
mk:orchestrate is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 133 tokens to every session and 3,699 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
dispatch
Use when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy. Trigger with /hyperflow:dispatch, "run the plan", "execute the task", "build it"…
oma-recap
Analyze conversation histories from multiple AI tools (Grok, Claude, Codex, Gemini, Qwen, Cursor, Antigravity) and generate themed daily/period work summaries. Filter by date or time window.
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
himalaya
CLI to manage emails via IMAP/SMTP. Use himalaya to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
cron
A scheduler for tasks that should run automatically at a future time or repeat on a schedule. It uses cron expressions, a text format for describing times such as every day at 9:00.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.