feature-doc-review-panel

feature-doc-review-panel is a skill for Claude Code from ramybarsoum/prodkit. It costs 41 tokens per session (1,478 once invoked), scanned A, original, MIT.

A review panel that examines a feature document from seven viewpoints, including engineering, design, legal, user research, and customers. It uses separate agents to provide the feedback.

In plain words
What is it for?
Getting broad feedback on a feature proposal, checking its technical and user impact, and optionally adding architecture, data, operations, performance, security, and testing perspectives.
Why use it?
It exposes gaps, conflicting assumptions, and stakeholder concerns before the document reaches formal review.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

Part of the prodkit plugin — 10 skills shipped together

Good fit Getting broad feedback on a feature proposal, checking its technical and user impact, and optionally adding architecture, data, operations, performance, security, and testing perspectives.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ramybarsoum/prodkit/feature-doc-review-panel
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.

Any agent
npx skills add ramybarsoum/prodkit --skill feature-doc-review-panel
Clone the repo
git clone --depth 1 https://github.com/ramybarsoum/prodkit

Made for: Claude Code.

Or install prodkit, the plugin that ships this one along with the rest of its 10 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 feature-doc-review-panel

README.md
[![agentmods](https://agentmods.dev/badge/skills/ramybarsoum/prodkit/feature-doc-review-panel/github.svg)](https://agentmods.dev/skills/ramybarsoum/prodkit/feature-doc-review-panel)
Your own site
<a href="https://agentmods.dev/skills/ramybarsoum/prodkit/feature-doc-review-panel"><img src="https://agentmods.dev/badge/skills/ramybarsoum/prodkit/feature-doc-review-panel/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 feature-doc-review-panel

Your own site · 80×15
<a href="https://agentmods.dev/skills/ramybarsoum/prodkit/feature-doc-review-panel"><img src="https://agentmods.dev/badge/skills/ramybarsoum/prodkit/feature-doc-review-panel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,478 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 $0.00041 $0.01478
Opus 5 $0.00020 $0.00739
Sonnet 5 $0.00008 $0.00296
Haiku 4.5 $0.00004 $0.00148

Measured 8d ago against content hash 9e83ca7fc0ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

feature-doc-review-panel 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.

skills/feature-doc-review-panel/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interaction style: Use the AskUserQuestion tool for all structured questions in this skill. Group related questions together (2-3 per call) rather than asking one at a time.

Purpose

Get comprehensive feedback on your Feature Doc from 7 different perspectives in parallel: Engineering, Design, Executive, Legal, UX Research, Skeptic, and Customer Voice.

Catches gaps, challenges assumptions, and surfaces conflicts before stakeholder review.

Usage

  • /feature-doc-review-panel - Review a Feature Doc with all 7 sub-agents
  • /feature-doc-review-panel [file-path] - Review specific Feature Doc by path
  • /feature-doc-review-panel --perspectives "eng,design,exec" - Review with subset of agents
  • /feature-doc-review-panel --extended - Include 6 additional perspectives (architecture, data, devops, performance, security, testing)

Execution Steps

Step 1: Locate the Feature Doc

If a file path was provided as an argument, use that. Otherwise:

  1. Search for Feature Docs in the workspace: Glob("**/FEATURE-DOC.md"), Glob("**/feature-doc*.md"), Glob("projects/**/FEATURE-DOC.md")
  2. If multiple found, ask the user which one to review using AskUserQuestion
  3. If none found, ask the user to provide the path or paste the content

Read the full Feature Doc content. Store it as FEATURE_DOC_CONTENT.

Step 2: Load context files (if they exist)

Attempt to read these context files. Skip any that don't exist:

  • reference/company/product-principles.md (product principles to evaluate against)
  • reference/company/business-info.md (company context)
  • reference/strategy/ (any strategy docs)

Combine available context into CONTEXT_SUMMARY (keep it under 500 words).

Step 3: Determine which perspectives to run

Default 7 (core panel):

Perspective Sub-Agent File Key
Engineering _system/sub-agents/engineer-reviewer.md eng
Design _system/sub-agents/designer-reviewer.md design
Executive _system/sub-agents/executive-reviewer.md exec
Legal _system/sub-agents/legal-advisor.md legal
UX Research _system/sub-agents/uxr-analyst.md uxr
Skeptic _system/sub-agents/skeptic.md skeptic
Customer Voice _system/sub-agents/customer-voice.md customer

Read the full file on GitHub · 171 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 · 171 lines · 41 tokens per session scan A 9e83ca7fc0ca

Subscribe to this mod's changes

feature-doc-review-panel is a skill published in the GitHub repository ramybarsoum/prodkit (4 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 1,478 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 skills, from other repositories

respect

2-mode UI respect skill — brief (generate RESPECT.md design brief before coding) and checkpoint (final pre-ship gate enforcing user-respect via α/β/γ gate matrix). Use --mode brief when starting any UI screen; use --mode checkpoint before shipping. RESPECT.md absence blocks craft-lint (exit 2).

kimsanguine/hplan · 70 tokens

design-token

A two-step process for documenting a product’s visual direction and design rules. It first gathers and filters design references into a brief, then turns that direction into reusable design tokens such as colors, spacing, and typography choices.

kimsanguine/hplan · 46 tokens

customer-journey-map

Visualize every touchpoint a customer has with a product or service — stages, actions, emotions, pain points, opportunities.

tupe12334/instinct · 31 tokens

double-diamond

Design problems with two diamond phases: Discover/Define (right problem), Develop/Deliver (right solution).

tupe12334/instinct · 25 tokens

design-spatial

Spatial composition and layout for frontend design. Load with design when composing pages/dashboards/components, or whenever generated UI looks off — overlapping/colliding elements, weak hierarchy, or generic ("looks like every startup site"). The core idea: a model can't trust its own layout, so render it, critique…

connerkward/ckw-design-skill · 0 tokens

design-system

Mechanical implementation invariants for frontend design: token architecture, typography hierarchy, loading order, FOUT prevention, chrome stability, motion timing, color semantics. Use with design when building components, pages, or design systems. (Aesthetic direction lives in design-thinking; anti-trend/anti-slop…

connerkward/ckw-design-skill · 67 tokens