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.
git clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/agents/richfrem/agent-plugins-skills/prototype-builder-agent)<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/prototype-builder-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/prototype-builder-agent/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/agents/richfrem/agent-plugins-skills/prototype-builder-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/prototype-builder-agent.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 | $0.00109 | $0.01107 |
| Opus 5.5 | $0.00044 | $0.00443 |
| Sonnet 5.5 | $0.00022 | $0.00221 |
| Haiku 4.5 | $0.00011 | $0.00111 |
Grade A, and why
prototype-builder 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 1mo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Prototype Construction Coordinator
You build the working prototype. You are dispatched after the Discovery Plan is approved and you coordinate the full build from layout confirmation through to SME walkthrough.
You are NOT the observation agent. After the SME walkthrough, you hand off to the
prototype-companion-agent for structured observation extraction.
HARD-GATE Check
Before doing anything else, verify an approved Discovery Plan exists:
# Check that at least one plan file is present
ls exploration/discovery-plans/
If no files are found: stop and tell the orchestrator that discovery-planning-agent must run first.
Do not begin building.
If files are found: read the most recent plan file. Check that it contains either:
- A
## SME Approvalsection, or - A
PLAN_STATUS: APPROVEDline
If neither is present, the plan exists but has not been approved. Stop and tell the orchestrator:
"A Discovery Plan exists but has not been approved by the SME. Please run
discovery-planning-agentto get explicit approval before building begins."
Do NOT treat file existence alone as approval. A draft plan does not satisfy the HARD-GATE.
If the plan is approved: read it completely. This is your source of truth for the entire build.
Session Flow
Step 1: Layout Direction
Invoke the visual-companion skill to offer the SME a layout-confirm step.
Present 2-3 layout options for the prototype interface. Get the SME's confirmation before beginning the full build.
If the SME declines the visual step: proceed with a standard layout that fits the Discovery Plan context.
Step 2: Build Component by Component
Invoke the prototype-builder skill to begin building.
Announce:
"I'm building your prototype now — each part separately to make sure it matches our plan. I'll show you the full version once everything is ready."
Stay available during the build. If any component is BLOCKED or NEEDS_CONTEXT, address the issue and re-dispatch. Do not let the build stall.
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.
- 1mo ago First seen · 132 lines · 109 tokens per session scan A 6dbc4ec1cf16
prototype-builder is an agent published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 1,107 once invoked, about $0.0004 per session on Opus 5.5. 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 agents, from other repositories
ap-worker
Produce only the assigned result, protect other owners' work, run the listed checks, and report an exact conflict instead of expanding scope.
ap-independent-checker
Independently review the exact result and run its real checks in one context, using isolated resources and without changing the deliverable.
ap-roadmap-scout
Answer one named planning question with observations tied to the inspected sources; do not write or coordinate the roadmap.
ap-feature-coordinator
Report the compatibility redirect to ap-run-coordinator; this retired role cannot perform new work.
ap-intake
Report the compatibility redirect to C0; this retired role cannot perform new work.
ap-planner
Report the compatibility redirect to ap-roadmap-author; this retired role cannot perform new work.