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 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/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/skills/wellapp-ai/well/competitor-scan"><img src="https://agentmods.dev/badge/skills/wellapp-ai/well/competitor-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.5 | $0.00006 | $0.00268 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo 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 (345 stars, last pushed 6d ago), licensed MIT. It adds 16 tokens to every session and 671 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 2026-08-30.
Other skills, from other repositories
auto-reader-ocr
Extract text from images/PDFs (Arabic-first, manga-aware Japanese, 13+ languages auto-detected), translate between 100+ languages, and pull structured fields from invoices/receipts/IDs via the Auto-Reader OCR API. Use when the user shares a document image or PDF to read, translate, or extract data from — or asks for…
api-integration-architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
non-json-content-types
Handle FormData, file uploads, Blob, Uint8Array, and ReadableStream inputs in tRPC mutations. Use octetInputParser from @trpc/server/http for binary data. Route non-JSON requests with splitLink and isNonJsonSerializable() from @trpc/client. FormData and binary inputs only work with mutations (POST).
mirrord-prev-env
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer…
horse-integration-tests
Guide for writing automated integration tests for Horse endpoints using DUnit/DUnitX and THTTPClient.
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.