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.
npx agentmods add skills/wellapp-ai/well/competitor-scannpx skills add WellApp-ai/Well --skill competitor-scangit clone --depth 1 https://github.com/WellApp-ai/WellWrote 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/skills/wellapp-ai/well/competitor-scan)<a href="https://agentmods.dev/skills/wellapp-ai/well/competitor-scan"><img src="https://agentmods.dev/badge/skills/wellapp-ai/well/competitor-scan.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.00671 |
| Opus 5 | $0.00008 | $0.00336 |
| Sonnet 5 | $0.00003 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
competitor-scan 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 6d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitor Scan Skill
Research how best-in-class products solve similar problems using Browser MCP for screenshots and WebSearch for teardowns.
When to Use
- At the start of DIVERGE Loop (L1)
- When exploring new UI patterns
- When benchmarking against industry standards
Instructions
Phase 1: Identify Competitors
Use the domain competitor table:
| Domain | Products to Study |
|---|---|
| Workspaces/Collaboration | Notion, Linear, Slack, Figma, Attio |
| Data Tables | Airtable, Retool, Rows, Grist |
| AI Chat | ChatGPT, Claude, Gemini, Perplexity |
| Onboarding/Flows | Stripe, Plaid, Mercury, Ramp |
| Settings/Admin | Vercel, Railway, PlanetScale |
| Invitations/Team | Slack, Notion, Linear, Figma |
| Billing/Subscriptions | Stripe, Paddle, Chargebee |
Phase 2: Screenshot Key Flows (Browser MCP)
For each relevant competitor:
1. browser_navigate to the product URL or relevant page
2. browser_snapshot to understand the page structure
3. browser_take_screenshot to capture the UI
4. browser_click / browser_type to navigate through flows
Capture:
- Entry points (how users start the flow)
- Key screens (main interactions)
- Edge cases (empty states, errors)
- Micro-interactions (hover states, transitions)
Phase 3: Research Teardowns (WebSearch)
Search for existing analysis:
WebSearch "[Product] UI teardown [feature]"
WebSearch "[Product] UX case study [feature]"
WebSearch "[Feature] best practices design patterns"
Phase 4: Extract Patterns
For each competitor, note:
| Aspect | Pattern |
|---|---|
| Layout | How is content organized? |
| Navigation | How do users move between states? |
| Actions | How are primary/secondary actions presented? |
| Feedback | How is success/error communicated? |
| Copy | What language/tone is used? |
Output Format
After running this skill, output:
## Competitor Scan
### Products Analyzed
1. [Product A] - [URL or feature]
2. [Product B] - [URL or feature]
3. [Product C] - [URL or feature]
### Key Patterns Observed
| Pattern | Product | Description |
|---------|---------|-------------|
| [Pattern] | [Product] | [How they do it] |
### Insights for Our Design
- [Insight 1]: [How to apply]
- [Insight 2]: [How to apply]
### Screenshots Captured
- [Description of screenshot 1]
- [Description of screenshot 2]
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.
- 6d ago First seen · 106 lines · 16 tokens per session scan A e88d1d7b0245
competitor-scan is a skill published in the GitHub repository WellApp-ai/Well (340 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 671 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
voiden
Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.
qa
QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.
composio
Build AI agents and apps with Composio - access 200+ external tools with Tool Router or direct execution.
geoserver-rest-api
Use when automating GeoServer management — programmatic workspace, datastore, and layer creation, style upload, service configuration via REST API. GeoServer REST API: manage GeoServer without GUI using curl, Python, or any HTTP client.
replicate-runner
Use when run AI models on Replicate cloud API. Deploy image generation, video creation, audio processing, and custom models without managing infrastructure. Use when working with replicate runner.