subagent-driven-prototyping

subagent-driven-prototyping is a skill for Claude Code, Codex from richfrem/agent-plugins-skills. It costs 74 tokens per session (3,390 once invoked), scanned A, original, MIT.

A step-by-step prototyping workflow that builds interface components one at a time and checks each against an approved plan.

In plain words
What is it for?
Use it to implement a prototype in small pieces after the layout direction has been confirmed.
Why use it?
It keeps a prototype aligned with the agreed layout and catches mismatches before more parts are built.

Skill for Claude CodeCodex

Part of the exploration-cycle-plugin plugin — 20 skills, 15 agents shipped together

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 skills/richfrem/agent-plugins-skills/subagent-driven-prototyping
Any agent
npx skills add richfrem/agent-plugins-skills --skill subagent-driven-prototyping
Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

Made for: Claude Code, Codex.

Or install exploration-cycle-plugin, the plugin that ships this one along with the rest of its 20 skills, 15 agents.

Wrote 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.

agentmods badge for subagent-driven-prototyping

README.md
[![agentmods](https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/subagent-driven-prototyping.svg)](https://agentmods.dev/skills/richfrem/agent-plugins-skills/subagent-driven-prototyping)
Your own site
<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/subagent-driven-prototyping"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/subagent-driven-prototyping.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,390 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 $0.00074 $0.03390
Opus 5 $0.00037 $0.01695
Sonnet 5 $0.00015 $0.00678
Haiku 4.5 $0.00007 $0.00339

Measured yesterday against content hash e8524ed96eef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

subagent-driven-prototyping 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 yesterday.

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.

plugins/exploration-cycle-plugin/skills/subagent-driven-prototyping/SKILL.md · 244 lines

How it starts

The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architectural patterns adapted from obra/superpowers (MIT)

Dashboard Intercept

Before doing anything else, silently check for exploration/exploration-dashboard.md.

  • If the file EXISTS:
    • Read the file and check the status. If status is Complete, proceed standalone.
    • If status is In Progress or TBD:
      • Check for the presence of the <ORCHESTRATOR_DISPATCH> tag in the immediate context.
      • If the tag is PRESENT:
        • Extract and verify authorized_skill, phase_number, and expected_output.
        • If authorized_skill matches "subagent-driven-prototyping" AND phase_number matches the dashboard phase:
          • Proceed with this skill's logic. (You are authorized by the orchestrator).
          • Note: The orchestrator manages dispatch token lifecycle. This tag is valid for the current phase only — it becomes stale once the orchestrator advances the dashboard in Block 6.
        • If verification fails (mismatched name or stale phase):
          • Stop immediately. Announce: "Orchestrator dispatch verification failed. Returning to dashboard."
          • Return control. Invoke skill: exploration-workflow. Stop generating output.
      • If the tag is ABSENT or malformed:
        • Stop immediately. Do not continue.
        • Announce: "It looks like you have an active Exploration Session. Let me take you back to your session dashboard."
        • Return control to the orchestrator. Invoke skill: exploration-workflow. Stop generating output from this skill.
  • If the file DOES NOT exist: Proceed standalone.

Read the full file on GitHub · 244 lines

Files

What ships with it

8 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.

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. yesterday First seen · 244 lines · 74 tokens per session scan A e8524ed96eef

Subscribe to this mod's changes

subagent-driven-prototyping is a skill published in the GitHub repository richfrem/agent-plugins-skills (6 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 3,390 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 2026-09-03.