design-agent

A command for designing a new agent persona, repeatable workflow skill, or Pi harness. A persona sets an agent’s role, a skill defines a workflow, and a harness changes how a Pi session behaves.

In plain words
What is it for?
Use it to author files in `agents/`, `skills/`, or `.pi/harnesses/`. It guides the design and asks for confirmation before writing the files.
Why use it?
It helps turn an idea into a structured project artifact with a clear purpose, scope, output, and implementation pattern. It also checks existing files for overlap before drafting.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/chankov/agent-fleet/design-agent
Clone the repo
git clone --depth 1 https://github.com/chankov/agent-fleet

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00279
Opus 5 $0.00013 $0.00139
Sonnet 5 $0.00005 $0.00056
Haiku 4.5 $0.00003 $0.00028

Measured 2d ago against content hash b039f10a0913, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-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 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.

.versions/0.0.1/.claude/commands/design-agent.md · 15 lines

What it actually says

Invoke the agent-fleet:designing-agents skill.

Begin by understanding what the user wants to author:

  1. Is this a persona (a role/lens the agent adopts, e.g. a reviewer or auditor), a skill (a repeatable workflow with gated steps and verification), or a pi harness (a TypeScript pi extension that reshapes the session — footer, tool-call gate, new command, or orchestrator)?
  2. The one-sentence purpose and when it should be invoked
  3. The framework or steps — dimensions evaluated (persona), ordered workflow (skill), or session surface and events hooked (harness)
  4. Explicit non-goals and scope limits
  5. Output shape — what a typical invocation should produce

Then scan the target location (agents/, skills/, or .pi/harnesses/) for overlap, draft the artifact using the matching template — four-block persona structure, the section order from docs/skill-anatomy.md, or the harness pattern in skills/designing-agents/pi-harness-authoring.md — verify the draft against references/prompting-patterns.md, and confirm with the user before writing the file(s).

Changes

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.

  1. 2d ago First seen · 15 lines · 26 tokens per session scan A b039f10a0913

Subscribe to this mod's changes

design-agent is a command published in the GitHub repository chankov/agent-fleet (10 stars, last pushed 6d ago), licensed MIT. It adds 26 tokens to every session and 279 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 2026-08-31.