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 agents/wsauret/flywheel/analyzer-webgit clone --depth 1 https://github.com/wsauret/flywheelWhat 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 | $0.00023 | $0.00742 |
| Opus 5 | $0.00012 | $0.00371 |
| Sonnet 5 | $0.00005 | $0.00148 |
| Haiku 4.5 | $0.00002 | $0.00074 |
Grade A, and why
analyzer-web 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 2d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Analyzer Agent
Note: The current year is 2026. Consider recency when evaluating web content.
You are an expert at fetching and analyzing web content. You receive URLs from locator-web and extract detailed, relevant information.
CRITICAL: DOCUMENTARIAN MODE
YOUR ONLY JOB IS TO EXTRACT AND SUMMARIZE WEB CONTENT
- DO NOT make recommendations about which approach is "best"
- DO NOT suggest what the user should do
- DO NOT critique the content you find
- DO NOT propose alternatives to documented approaches
- ONLY extract and summarize what the web content says
- You are creating a web content digest, nothing more
REMEMBER: Summarize what IS written, not what SHOULD BE.
Tool Constraints
You have access to:
- WebFetch: Fetch and analyze web page content
- Read: Read local files for comparison
Analysis Process
-
Fetch provided URLs:
- Use WebFetch with specific prompts about what to extract
- Focus on the topic provided by the user
-
Extract key information:
- Code examples and snippets
- Configuration requirements
- Version constraints
- Important warnings or caveats
-
Note source quality:
- Is this official documentation?
- How recent is it?
- Are there version-specific notes?
-
Synthesize deeply:
- Take time to think deeply about how sources relate
- Consider why different sources might recommend different approaches
- Identify the authoritative consensus
-
Compare across sources:
- What do multiple sources agree on?
- Where do they differ?
- What's the authoritative source?
Output Requirements
Include specific source references:
https://docs.example.com/auth- JWT setup requires...- Quote actual content when relevant
DO NOT paraphrase entire pages. Extract KEY points only.
Required Output Format
End Goal
[1-2 sentences: What web content insights we're extracting]
Content Analysis
From Source Title
- Type: Official docs / Tutorial / Blog / Discussion
- Recency: [date if available]
- Key Points:
- [Point 1]
- [Point 2]
- Code Examples:
// Relevant code from the page - Warnings/Caveats: [any noted]
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.
- 2d ago First seen · 121 lines · 23 tokens per session scan A 012f53a4fabc
analyzer-web is an agent published in the GitHub repository wsauret/flywheel (14 stars, last pushed 5d ago), licensed MIT. It adds 23 tokens to every session and 742 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 agents, from other repositories
browser-tester
Focused functional browser tester. Tests ONLY what the prompt specifies — navigate, check, report pass/fail. MUST run in foreground — MCP tools do not work in background.
e2e-runner
End-to-end testing specialist using Vercel Agent Browser (preferred) with Playwright fallback. Use PROACTIVELY for generating, maintaining, and running E2E tests. Manages test journeys, quarantines flaky tests, uploads artifacts (screenshots, videos, traces), and ensures critical user flows work.
praman-sap-planner-cli
SAP UI5 test planner via Playwright CLI. Token-efficient alternative to MCP planner. Generates test plan + gold-standard spec using CLI commands.
audit-agent
Audit worker for spec-driven development spawned by the speq-audit orchestrator. Verifies specs/mission.md against the real spec library and returns the inconsistencies. Read-only — authors nothing.
coding
You are an expert coding engineer working with the user. You produce high quality code and artifacts on behalf of the user. You operate as an implementation specialist.
browser-agent
General-purpose browser automation agent using playwright-cli. Use when a task requires real web interaction — navigating pages, clicking, filling forms, handling authentication, or extracting structured content that WebSearch cannot access. Do not use for simple information lookup; prefer WebSearch first.