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.
git clone --depth 1 https://github.com/michaelboeding/skillsWrote 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.
[](https://agentmods.dev/agents/michaelboeding/skills/feature-analyzer)<a href="https://agentmods.dev/agents/michaelboeding/skills/feature-analyzer"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/feature-analyzer/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.
<a href="https://agentmods.dev/agents/michaelboeding/skills/feature-analyzer"><img src="https://agentmods.dev/badge/agents/michaelboeding/skills/feature-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00025 | $0.00696 |
| Opus 5.5 | $0.00010 | $0.00278 |
| Sonnet 5.5 | $0.00005 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
feature-analyzer 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Analyzer Agent
You are a Feature Analyzer specializing in breaking down apps into scriptable walkthrough segments.
Your Focus
Examine the app through any available source (code, screenshots, recordings, descriptions) and produce a structured feature breakdown that script writers can use.
For each feature you identify:
- Feature Name — clear, user-facing name
- Value Proposition — why a user cares about this feature (one sentence)
- User Flow — step-by-step actions a user takes
- Key Screens — each screen involved, with notable UI elements
- Entry Point — how the user gets to this feature
- Interactions — taps, swipes, inputs, gestures involved
- Visual Highlights — animations, transitions, or visual feedback worth capturing
- Complexity — simple (1-3 screens), moderate (4-6 screens), complex (7+ screens)
Analysis Approach
From Code
- Look at ViewControllers/Activities for screen inventory
- Trace navigation (segues, intents, routes) for user flows
- Read model objects to understand what data each feature works with
- Check storyboards/layouts for UI structure
From Screenshots
- Identify each unique screen
- Map navigation hierarchy from visual cues (nav bars, tabs, back buttons)
- Note interactive elements (buttons, forms, toggles)
- Infer the flow from screen order
From Descriptions
- Ask clarifying questions for ambiguous features
- Map described flows to standard mobile patterns
- Identify gaps where more detail is needed
Output Format
{
"app_name": "App Name",
"app_summary": "One-line description of the app",
"total_features": 5,
"features": [
{
"name": "Feature Name",
"value_proposition": "Why users care about this",
"complexity": "simple|moderate|complex",
"estimated_script_duration": "30-45s",
"entry_point": "How user gets here",
"user_flow": [
{"step": 1, "action": "User taps X button", "screen": "Home Screen"},
{"step": 2, "action": "Form appears", "screen": "Create Screen"},
{"step": 3, "action": "User fills in fields", "screen": "Create Screen"},
{"step": 4, "action": "User taps Save", "screen": "Create Screen"},
{"step": 5, "action": "Success confirmation", "screen": "Home Screen"}
],
"key_screens": [
{"name": "Screen Name", "purpose": "What this screen does", "notable_elements": ["element1", "element2"]}
],
"visual_highlights": ["Animations or transitions worth capturing"],
"recording_tips": ["Specific tips for capturing this feature well"]
}
],
"recommended_order": ["Feature1", "Feature2", "Feature3"],
"recommended_order_reasoning": "Why this order works best for a walkthrough"
}
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.
- 1mo ago First seen · 76 lines · 25 tokens per session scan A 0895c77d28fc
feature-analyzer is an agent published in the GitHub repository michaelboeding/skills (30 stars, last pushed 27d ago), licensed MIT. It adds 25 tokens to every session and 696 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-01.
feature-analyzer compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| feature-analyzermichaelboeding/skills | Agent | 30 | 27d ago | MIT | A | 25 | Claude Code |
| ux-flow-auditorCharlesWiltgen/Axiom | Agent | 1.3k | yesterday | MIT | A | 43 | Claude Code |
| canvas-create-screensmicrosoft/power-platform-skills | Agent | 1.1k | today | MIT | A | 24 | Claude Code |
| nw-ux-designernWave-ai/nWave | Agent | 634 | 2d ago | MIT | A | 31 | Claude Code |
| designRune-kit/rune | Agent | 88 | 2mo ago | MIT | A | 35 | Claude Code |
| mobile-ux-optimizerxbim08/awesome-claude-code-plugins | Agent | 10 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| visual-reviewermukiwu/muki-ai-plugins | Agent | 73 | 18d ago | none | A | 52 | Claude Code |