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 ntorga/agent-starter-kit --skill dispatchgit clone --depth 1 https://github.com/ntorga/agent-starter-kitWrote 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/ntorga/agent-starter-kit/dispatch)<a href="https://agentmods.dev/skills/ntorga/agent-starter-kit/dispatch"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/dispatch/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/ntorga/agent-starter-kit/dispatch"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/dispatch.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 | $0.00018 | $0.02470 |
| Opus 5 | $0.00009 | $0.01235 |
| Sonnet 5 | $0.00004 | $0.00494 |
| Haiku 4.5 | $0.00002 | $0.00247 |
Grade A, and why
dispatch 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 2d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Every sub-agent starts cold. It has no rules, no memory, and no awareness of the project it is about to work on. This skill defines how the Maestro assembles the initial prompt that boots a sub-agent into a ready state, and routes it to the correct provider based on the persona's preferred model.
Terminology
A sub-agent is a persona defined in this framework — nothing else. The terms "sub-agent" and "persona" are interchangeable throughout this skill. Sub-agents are not host-runtime features (IDE subprocesses, tool-provided agents, or built-in workers). The Maestro must never route work to a host-runtime agent when a framework persona exists for the job.
To discover available sub-agents, read:
personas/README.md— lists every persona and its purpose.
This is the only registry. If a persona is not listed there, it does not exist. The Maestro must consult this registry during the Route step before dispatching.
Procedure
-
Identify the host runtime. Run
ps -p $PPID -o comm=and match the process name against the CLI column of the Providers list to identify the host runtime's provider (e.g.,opencode→opencodehost,claude→claudeprovider,codex→codexprovider,cursor-agent→cursorprovider). Store the result in session state — the host runtime does not change mid-conversation. -
Extract routing fields.
sed -n '/^---$/,/^---$/{ /^\(preferredModel\|modelTier\):/p }' personas/<name>.md -
Select the provider and model. Resolve
preferredModelandmodelTieragainst the Providers list. IfpreferredModelishost, always use native dispatch — the persona runs on whatever model the host runtime provides, ignoring tier upgrades. IfpreferredModelis omitted, use the host runtime's provider. The persona'smodelTieris a floor — upgrade one tier when the task demands multi-step reasoning across system boundaries (e.g., cross-layer architectural changes, security/auth logic, or production deployment pipelines). If already at tier-3, remain at tier-3.
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.
- 2d ago First seen · 163 lines · 18 tokens per session scan A 149c0da5270e
dispatch is a skill published in the GitHub repository ntorga/agent-starter-kit (142 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 2,470 once invoked, about $0.0001 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 2026-09-13.
Other skills, from other repositories
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
python-package-management
Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
verify-samples-tool
How to use the verify-samples tool to run, verify, and manage sample definitions in the Agent Framework repository. Use this when adding, updating, or running sample verification.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.