agent-design skillA
agent-design is agent-read markdown (skill) from nahid-sparktales/agent-dispatcher: Scope an agent or subagent before it is built — the one job it owns, the smallest tool set that closes that job, what it must never do, and the evidence it has to return. Use when adding an agent, subagent or automated role to a system, when deciding which tools it gets, when an existing agent loops, over-reaches or reports work it did not do, or when reviewing someone else's agent design. Not for wording the prompt itself, not for deciding what occupies its context window, and it never grants a.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Agent design Most agent failures are design failures wearing a prompt's clothing. An agent with two jobs, a tool it did not need, or no definition of done will fail in ways no amount of rewording fixes. ## When this fires Before writing an agent's instructions: a new agent or subagent, a new tool granted to an existing one, or a review of one that misbehaves. It does not fire for a single prompt with no tools and no loop — that is `prompt-engineering`. ## Procedure 1. **State the job in one sentence with a done condition.** "Finds the failing test and reports which commit introduced it" is a job. If the sentence needs an "and", you have two agents, or one agent and a chain. Split before designing further. 2. **Draw the boundary in both directions.** What it receives, what it returns, and — named explicitly — what it does not do and who does that instead. An agent without a stated non-responsibility will grow into whatever is adjacent. 3. **Pick the autonomy level before the tools.** Three honest settings: proposes and stops; acts within a reversible sandbox and reports; acts and reports. Anything destructive, outward-facing, …
Read the whole file at its exact version.
How to install
mdr add nahid-sparktales/agent-dispatcher/agent-design@git:20260919.a0d4f55mdr add nahid-sparktales/agent-dispatcher/agent-design@sha256:109c7e9cc619f0d8Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_ufju2f7ymo6ifgjf)
1 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6423 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
nahid-sparktales/agent-dispatcher · 49 stars · license MIT · pushed 2026-09-23 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ufju2f7ymo6ifgjf GET https://markdownregistry.com/api/v1/resolve?ref=nahid-sparktales/agent-dispatcher/agent-design GET https://markdownregistry.com/api/v1/blob/109c7e9cc619f0d82693d45fee0ebf97b97ef5df02127ea8016af1b7493c3999
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
More from nahid-sparktales/agent-dispatcher
Every file in nahid-sparktales/agent-dispatcher