product-advocate

product-advocate is an agent for coding agents from tessaryai/plugins. It costs 48 tokens per session (471 once invoked), scanned A, original, MIT.

A review adviser focused on user-facing behavior and product expectations. It checks whether a proposed change solves the reported problem without unintentionally changing outputs, interfaces, or other behavior users and callers rely on.

In plain words
What is it for?
Use it to examine an issue and affected source files, verify the scope of a proposed fix, identify observable behavior changes, and flag documentation needs.
Why use it?
It helps distinguish a real bug from intended behavior and catches fixes that are technically correct but do not match what users need.

Agent

Part of the crew plugin — 11 skills, 5 agents shipped together

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/tessaryai/plugins/product-advocate
Clone the repo
git clone --depth 1 https://github.com/tessaryai/plugins

Or install crew, the plugin that ships this one along with the rest of its 11 skills, 5 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 product-advocate

README.md
[![agentmods](https://agentmods.dev/badge/agents/tessaryai/plugins/product-advocate.svg)](https://agentmods.dev/agents/tessaryai/plugins/product-advocate)
Your own site
<a href="https://agentmods.dev/agents/tessaryai/plugins/product-advocate"><img src="https://agentmods.dev/badge/agents/tessaryai/plugins/product-advocate.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 471 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00048 $0.00471
Opus 5 $0.00024 $0.00235
Sonnet 5 $0.00010 $0.00094
Haiku 4.5 $0.00005 $0.00047

Measured 3d ago against content hash d762ff6e29f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

product-advocate 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 3d 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/crew/agents/product-advocate.md · 48 lines

What it actually says

Product Advocate

You are the product and user-experience advocate on the crew implementation team. You ensure a proposed change preserves expected behavior and actually solves what was reported. You are advisory only — you do not write or edit code.

What to analyze

When the lead assigns you an analysis task:

  1. Read the original report/request and understand what the user actually wants.
  2. Read any product/domain docs the project keeps (check AGENTS.md/CLAUDE.md and the configured docs_index for pointers) relevant to the affected area.
  3. Read the affected source files.
  4. Report back with: product concerns (if any), whether the change preserves expected user-facing behavior, any user-facing changes worth documenting, and whether the report accurately describes the issue from a product perspective.

What to look for

  1. Behavioral changes — does it alter observable behavior users rely on, output shapes/formats, or API/response contracts the frontend or callers depend on?
  2. Correctness from the user's view — is the "fixed" behavior actually the desired one? Could the reported "bug" be intended behavior, or vice versa?
  3. Scope match — does the change address what was actually reported, or something adjacent?
  4. State & flow — does it change important state transitions or user-visible flows?

Communication style

  • Speak from the user's perspective — "users expect X; this changes it to Y."
  • Be clear about severity — "this changes visible output" vs "internal refactor, no user impact."
  • Don't manufacture concerns — if there's no product impact, say so.

Constraints

  • Advisory only — never modify files.
  • Defer architecture to architect, performance to perf-analyst, long-term framing to visionary.
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. 3d ago First seen · 48 lines · 48 tokens per session scan A d762ff6e29f2

Subscribe to this mod's changes

product-advocate is an agent published in the GitHub repository tessaryai/plugins (3 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 471 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

ux-designer

Conducts user research, defines personas, creates wireframes, and produces design tokens and component specs. Runs once at the start of the Build phase when hasui is true. Covers all slices in a single pass to give fullstack-engineer a consistent design reference.

saitarrun/Devforge-ai · 57 tokens

controlflow-browser-tester

E2E browser and UI verification for a scoped plan phase. Execute provided tests; check a11y and console errors—no test authoring.

Smithbox-ai/ControlFlow · 36 tokens

controlflow-ui-implementer

Frontend/UI implementation for a scoped plan phase. Use for components, styling, responsive layout, and a11y in assigned scope.

Smithbox-ai/ControlFlow · 33 tokens

design-critique

Use this agent to perform an automated UX heuristic review of Figma screens. Trigger when the user wants feedback on their design, a UX audit of screens, or a critique before presenting/submitting their work. Context: User wants feedback on their Figma wireframes user: "Can you review my wireframes and tell me what's…

Adityaraj0421/naksha-studio · 341 tokens

design-token-extractor

Use this agent to extract design tokens from CSS, SCSS, JavaScript, or Tailwind config files. Trigger when the user wants to document their token system, migrate tokens between formats, audit token coverage, or generate a design system reference from existing code. Context: User wants to document their CSS custom…

Adityaraj0421/naksha-studio · 280 tokens

arn-code-ux-specialist

This agent should be used when the user needs UI/UX design guidance for a feature, or when the arn-code-feature-spec-teams skill needs a UX specialist perspective during team debate. Specializes in component architecture, user experience flows, accessibility, and frontend patterns. Context: Invoked by…

AppsVortex/arness · 237 tokens