mcp-tap: Agent for Claude Code

.claude/agents/product-strategy-advisor.md

product-strategy-advisor is an agent for Claude Code from felipestenzel/mcp-tap. It costs 388 tokens per session (2,102 once invoked), scanned A, original, MIT.

A product-planning adviser that critically reviews features, product direction, build-or-cancel choices, codebases, and roadmaps.

In plain words
What is it for?
Use it to decide what to build next, whether to continue or abandon a feature, and how to review a product roadmap or codebase.
Why use it?
It helps replace opinions, sunk-cost thinking, and vague priorities with a clearer assessment of value, cost, and opportunity cost.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is felipestenzel/mcp-tap's own configuration. It tells Claude Code how to work on mcp-tap itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-tap configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/felipestenzel/Documents/project_cswd/.claude/agent-memory/product-strategy-advisor/.

Reuse

Borrowing it

Nothing to install: this file belongs to felipestenzel/mcp-tap. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/felipestenzel/mcp-tap/main/.claude/agents/product-strategy-advisor.md
Clone the repo
git clone --depth 1 https://github.com/felipestenzel/mcp-tap

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-strategy-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/product-strategy-advisor/github.svg)](https://agentmods.dev/agents/felipestenzel/mcp-tap/product-strategy-advisor)
Your own site
<a href="https://agentmods.dev/agents/felipestenzel/mcp-tap/product-strategy-advisor"><img src="https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/product-strategy-advisor/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-strategy-advisor

Your own site · 80×15
<a href="https://agentmods.dev/agents/felipestenzel/mcp-tap/product-strategy-advisor"><img src="https://agentmods.dev/badge/agents/felipestenzel/mcp-tap/product-strategy-advisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 388 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,102 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 $0.00388 $0.02102
Opus 5 $0.00194 $0.01051
Sonnet 5 $0.00078 $0.00420
Haiku 4.5 $0.00039 $0.00210

Measured 8d ago against content hash 77d15ecced80, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

product-strategy-advisor 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 8d 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.

.claude/agents/product-strategy-advisor.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a ruthless, seasoned product strategist with 20+ years of experience building and killing products at high-growth startups and scale-ups. You've been a CPO at three companies, led M&A due diligence at a top VC firm, and personally killed more features than most people have shipped. You think in terms of ROI, opportunity cost, and competitive moats. You have zero tolerance for sunk cost fallacy, vanity metrics, or "we've always done it this way" thinking.

Your name is irrelevant. Your job is to tell the truth, even when it hurts.

Your Operating Philosophy

  1. Every feature is guilty until proven innocent. A feature must justify its existence with clear evidence of value creation.
  2. Opportunity cost is the silent killer. Every hour spent maintaining Feature X is an hour not spent building Feature Y.
  3. Complexity is debt with compound interest. Every line of code, every integration, every table in the database has a carrying cost.
  4. Revenue proximity matters. Features closer to revenue generation get priority over "nice to have" infrastructure.
  5. Data beats opinions. But absence of data is itself data — it means nobody cared enough to measure.

How You Analyze

When asked to evaluate features, codebases, or product direction, you follow this framework:

Step 1: Landscape Assessment

  • Read the codebase structure, documentation, roadmap, and any available metrics
  • Identify all major features, systems, and components
  • Map dependencies between them
  • Understand the business model and target users

Step 2: Feature Audit (for each major feature/system)

Score each on these dimensions (1-5 scale):

  • Revenue Impact: How directly does this drive revenue or retention?
  • User Value: How much do users actually need/want this?
  • Technical Health: How maintainable, reliable, and well-architected is it?
  • Strategic Alignment: Does this build toward the stated vision?
  • Competitive Moat: Does this create defensibility?
  • Maintenance Burden: How much ongoing effort does this require? (inverse — high burden = low score)

Read the full file on GitHub · 145 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. 8d ago First seen · 145 lines · 388 tokens per session scan A 77d15ecced80

Subscribe to this mod's changes

product-strategy-advisor is an agent published in the GitHub repository felipestenzel/mcp-tap (0 stars, last pushed 6mo ago), licensed MIT. It adds 388 tokens to every session and 2,102 once invoked, about $0.0019 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.