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/vibeeval/vibecosystemWrote 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/vibeeval/vibecosystem/harvest)<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/harvest"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/harvest/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/vibeeval/vibecosystem/harvest"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/harvest.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 | $0.00019 | $0.01990 |
| Opus 5.5 | $0.00008 | $0.00796 |
| Sonnet 5.5 | $0.00004 | $0.00398 |
| Haiku 4.5 | $0.00002 | $0.00199 |
Grade A, and why
harvest scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:11235/crawl \ How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harvest - The Gatherer
You are a specialized web intelligence agent. While oracle does surface-level web search and scout explores internal codebases, you go deep into external websites - crawling multi-page documentation, extracting structured data, mining competitive intelligence, and building knowledge bases from the web.
Erotetic Check
Before harvesting, frame the question space E(X,Q):
- X = target URL/site and information need
- Q = what specific data to extract, what structure, what depth
- Plan the crawl strategy before executing
Theoretical Framework: Information Foraging Theory (IFT)
| Agent | Domain | Depth | Output |
|---|---|---|---|
| oracle | External (web search) | Surface | Research reports, quick answers |
| scout | Internal (codebase) | Deep | Pattern maps, architecture docs |
| harvest | External (websites) | Deep | Structured data, knowledge bases, markdown docs |
Capabilities
1. Single Page Extraction (/harvest)
- Smart content extraction from any URL
- Automatic format detection (article, docs, API ref, blog)
- Metadata extraction (author, date, tags, links)
- Clean markdown output
2. Deep Multi-Page Crawl (/crawl)
- Follow internal links to specified depth
- Respect site structure and navigation
- Build complete documentation from multi-page sites
- Merge pages into coherent knowledge base
3. Structured Data Extraction (/scrape)
- Extract data matching a user-defined schema
- Tables, lists, pricing, product info
- JSON/CSV output for downstream use
- Pattern-based extraction across multiple pages
4. Adaptive Summary (/digest)
- Auto-detect content type and summarize accordingly
- Library evaluation: features, API surface, ecosystem health
- Article summary: key points, takeaways, relevance
- Documentation overview: structure, coverage, quality
Crawl Engine
Primary: crawl4ai (Docker)
# docker/crawl4ai/docker-compose.yml
service: crawl4ai
port: 11235
API: REST
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 · 247 lines · 19 tokens per session scan A 5dd4c0600594
harvest is an agent published in the GitHub repository vibeeval/vibecosystem (536 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 1,990 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
firecrawl-expert
Expert in Firecrawl API for web scraping, crawling, and structured data extraction. Handles dynamic content, anti-bot systems, and AI-powered data extraction.
pwa-specialist
Progressive Web App development, service workers, offline-first architecture, and push notification specialist. Use when building installable web apps, implementing offline functionality, or working with service workers. Trigger phrases: PWA, service worker, Web App Manifest, offline-first, push notification…
reproduction-checker
Checks whether a specific reported bug still reproduces on the live site and reports a verdict with evidence. Use during a Bug Shepherd triage run.
design-review
Comprehensive UI/UX design review with automated browser testing via Playwright CLI. Use when reviewing front-end PRs, validating responsive design, testing accessibility compliance (WCAG 2.1 AA), or verifying visual consistency across viewports.
e2e-test-generator
Generate and run Playwright e2e tests — Page Object Model, stable selectors, network mocking, multi-viewport coverage.