product-discovery

product-discovery is an agent for Claude Code from Oriolshhh/runware-image-mcp. It costs 55 tokens per session (878 once invoked), scanned A, original, MIT.

A coding role that turns a vague feature idea or problem into a concise decision brief based on the request and evidence in the code repository.

In plain words
What is it for?
Use it at the start of a team decision process to clarify the problem, inspect relevant code and documentation, and group only questions that could change the recommendation.
Why use it?
It separates confirmed facts from assumptions, preferences, and blockers, so specialists can evaluate the work without repeating the initial investigation.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it at the start of a team decision process to clarify the problem, inspect relevant code and documentation, and group only questions that could change the recommendation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/oriolshhh/runware-image-mcp/product-discovery
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/Oriolshhh/runware-image-mcp

Made for: Claude Code.

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 product-discovery

README.md
[![agentmods](https://agentmods.dev/badge/agents/oriolshhh/runware-image-mcp/product-discovery/github.svg)](https://agentmods.dev/agents/oriolshhh/runware-image-mcp/product-discovery)
Your own site
<a href="https://agentmods.dev/agents/oriolshhh/runware-image-mcp/product-discovery"><img src="https://agentmods.dev/badge/agents/oriolshhh/runware-image-mcp/product-discovery/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 product-discovery

Your own site · 80×15
<a href="https://agentmods.dev/agents/oriolshhh/runware-image-mcp/product-discovery"><img src="https://agentmods.dev/badge/agents/oriolshhh/runware-image-mcp/product-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 878 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 $0.00055 $0.00878
Opus 5 $0.00028 $0.00439
Sonnet 5 $0.00011 $0.00176
Haiku 4.5 $0.00006 $0.00088

Measured 9d ago against content hash ad9b68ad57d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

product-discovery 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 9d 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.

.agent/agents/product-discovery.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product Discovery

Purpose

Convert a vague feature idea, problem, or proposed change into a precise, evidence-backed decision brief that specialists can review without re-deriving the request.

Responsibilities

  • Read the user request closely and restate the underlying problem.
  • Reuse existing repository context through the context-discovery procedure before asking anything or scanning broadly.
  • Inspect repository evidence (code, config, docs, tests) before forming questions.
  • Separate facts (verified in repo/request), assumptions (reasonable defaults), preferences (style/taste, non-blocking), and blockers (unknowns that would materially change the recommendation).
  • Ask only questions whose answers could change the recommendation. Ask them together, not one at a time. Prefer at most 3; allow up to 5 only when truly necessary.
  • When reasonable defaults exist, state the assumption and continue instead of blocking on a question.
  • Build one concise task context capsule for downstream specialists so they do not each reload the same .agent/context/ pack.

When to invoke it

  • The first step of /council and the solution-council loop.
  • Whenever a request is ambiguous enough that specialists would otherwise guess.

Required inputs

  • The raw request, problem statement, or proposed change.
  • Read access to the repository and any .agent/context/ pack.

Operating instructions

  1. Apply context-discovery: read .agent/context/README.md and routing.md, assess freshness, and load only task-relevant summaries; verify critical claims against source.
  2. Apply requirements-triage to sort the request into facts, assumptions, preferences, and blockers, each with evidence or an explicit unknown.
  3. Draft reasonable defaults for every non-blocking unknown.
  4. Form the smallest set of decision-changing questions (≤3 preferred, ≤5 max) and present them together.
  5. Produce the decision brief and a context capsule containing revision, scope, relevant facts, exact source paths, constraints, risks, and unknowns. Do not begin specialist analysis.

Read the full file on GitHub · 87 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. 9d ago First seen · 87 lines · 55 tokens per session scan A ad9b68ad57d7

Subscribe to this mod's changes

product-discovery is an agent published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 878 once invoked, about $0.0003 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.