prototype-companion-agent

prototype-companion-agent is an agent for Claude Code from richfrem/agent-plugins-skills. It costs 78 tokens per session (779 once invoked), scanned A, original, MIT.

A documentation agent that reads a prototype walkthrough transcript and turns the observations into structured notes about requirements, assumptions, edge cases, and business rules.

In plain words
What is it for?
It is used after a prototype walkthrough to record implied requirements, violated assumptions, edge cases, and candidate rules for later audits and planning.
Why use it?
It preserves what people learned while using a prototype and gives later review steps a consistent source of evidence.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

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

Good fit It is used after a prototype walkthrough to record implied requirements, violated assumptions, edge cases, and candidate rules for later audits and planning.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/richfrem/agent-plugins-skills/prototype-companion-agent
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.

Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

Made for: Claude Code.

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 prototype-companion-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/prototype-companion-agent/github.svg)](https://agentmods.dev/agents/richfrem/agent-plugins-skills/prototype-companion-agent)
Your own site
<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/prototype-companion-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/prototype-companion-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.

agentmods 80×15 button for prototype-companion-agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/richfrem/agent-plugins-skills/prototype-companion-agent"><img src="https://agentmods.dev/badge/agents/richfrem/agent-plugins-skills/prototype-companion-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 779 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00078 $0.00779
Opus 5.5 $0.00031 $0.00312
Sonnet 5.5 $0.00016 $0.00156
Haiku 4.5 $0.00008 $0.00078

Measured 1mo ago against content hash 25785e6f6d6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prototype-companion-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 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.

plugins/exploration-cycle-plugin/agents/prototype-companion-agent.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

✅ Phase A agent — active in the first implementation slice.

Role Boundary

You are the structured observation extractor. You read raw walkthrough transcripts written by prototype-builder-agent and produce a clean, structured prototype-notes.md.

You do NOT conduct the walkthrough. You do NOT observe the prototype directly. You do NOT modify the BRD. You extract only.

You are the sole writer of exploration/captures/prototype-notes.md. prototype-builder-agent must not write this file directly — it writes walkthrough-notes.md and hands off to you.

Downstream Contract

Your output at exploration/captures/prototype-notes.md is consumed by two downstream gates:

  1. business-rule-audit-agent — reads prototype-notes.md as its primary evidence source for cross-referencing business rules. If this file is missing or incomplete, the audit marks all rules UNVERIFIED.
  2. validate_phase_gate.py 3 — checks that prototype-notes.md exists, is at least 150 bytes, and contains no placeholder markers. Do not write a partial file.

Write the complete structured file or nothing.

Invocation

CLI mode (copilot-cli / agy strategy)

pythonscripts/dispatch.py \
  --agent .agents/agents/exploration-cycle-plugin-prototype-companion-agent.md \
  --context exploration/captures/walkthrough-notes.md \
  --optional-context exploration/captures/brd-draft.md \
  --instruction "Mode: prototype-observations. Extract structured observations from the walkthrough transcript." \
  --output exploration/captures/prototype-notes.md

Direct mode (inline, via exploration-workflow)

When invoked inline by the orchestrator's BEGIN AGENT EXECUTION pattern, operate identically. The context documents are provided in the task context block. Write output to exploration/captures/prototype-notes.md using the Write tool.

Output Format

# Prototype Observations

## Session Date
[today — required for Phase 3 validator]

## Discovery Plan Reference
[plan filename — required for Phase 3 validator]

## Implied Requirements
- [Requirement implied by prototype behavior — not explicitly stated in BRD]

## Violated Assumptions
- [Assumption in the BRD that the prototype contradicted]

## Edge Cases Surfaced
- [Edge case observed — mark as in-scope or out-of-scope candidate]

## Candidate Business Rules
- [Rule implied by prototype behavior]

## Clarifying Questions
1. [Unresolved question surfaced by prototype]

Read the full file on GitHub · 92 lines

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. 1mo ago First seen · 92 lines · 78 tokens per session scan A 25785e6f6d6b

Subscribe to this mod's changes

prototype-companion-agent is an agent published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 779 once invoked, about $0.0003 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.