prototype-companion-agent

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

Phase A agent. Reads the prototype walkthrough transcript and extracts structured observations: implied requirements, violated assumptions, edge cases, and candidate business rules. Writes the canonical prototype-notes.md. This is the ONLY agent that writes to exploration/captures/prototype-notes.md …

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.

agentmods
npx agentmods add agents/richfrem/agent-plugins-skills/prototype-companion-agent
Clone the repo
git clone --depth 1 https://github.com/richfrem/agent-plugins-skills

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.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.svg" alt="Measured on agentmods" 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. Scan, not verified.
Origin unknown 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 $0.00078 $0.00779
Opus 5 $0.00039 $0.00390
Sonnet 5 $0.00016 $0.00156
Haiku 4.5 $0.00008 $0.00078

Measured today against content hash 25785e6f6d6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 today.

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. today 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 (6 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 779 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.

Related

Other agents, from other repositories

visual-architect

Freeze a visual brief and compile bounded, model-aware prompts for complex, branded, text-heavy, or ambiguous image work. Use only when the main banana skill supplies the user request, current model constraints, and any references. Never execute generation.

AgriciDaniel/banana-claude · 52 tokens

codebase-analyzer

Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :).

desplega-ai/agent-swarm · 44 tokens

codebase-locator

Locates files, directories, and components relevant to a feature or task. Call codebase-locator with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.

desplega-ai/agent-swarm · 68 tokens

web-search-researcher

Do you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the web-search-researcher subagenttype today to find any and all answers to your questions! It will research deeply to figure out and attempt to…

desplega-ai/agent-swarm · 114 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.

desplega-ai/agent-swarm · 47 tokens

canvas-layout

Spatial positioning specialist for Obsidian Canvas. Computes optimal node positions using layout algorithms (dagre, grid, radial, force-directed, linear). Preserves zone containment, snaps to 20px grid, refits groups. Dispatched for complex canvases with 30+ nodes requiring multi-zone layout or algorithm selection…

AgriciDaniel/claude-canvas · 132 tokens