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 instructions/konstantinmb/exploreyc/claude-mdgit clone --depth 1 https://github.com/KonstantinMB/exploreycWrote 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/instructions/konstantinmb/exploreyc/claude-md)<a href="https://agentmods.dev/instructions/konstantinmb/exploreyc/claude-md"><img src="https://agentmods.dev/badge/instructions/konstantinmb/exploreyc/claude-md.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 | $0.01144 | $0.01144 |
| Opus 5 | $0.00572 | $0.00572 |
| Sonnet 5 | $0.00229 | $0.00229 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
exploreyc CLAUDE.md 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 4d 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 -X POST http://localhost:8000/api/scrape \ How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
ExploreYC — a full-stack web app that scrapes Y Combinator's Algolia API for company data and provides analytics, AI-powered tools (idea validation, success prediction), interactive maps/charts, email digests, and a hiring board.
Tech Stack
- Frontend: React 19 + Vite 8 + TypeScript + Tailwind CSS (monospace/hacker theme with YC orange
#FF6600) - Backend: FastAPI (Python 3.11) — nearly all endpoints live in
backend/main.py - Database: SQLite locally, PostgreSQL (Supabase) in production — chosen via
database_factory.pybased onDATABASE_URL - Deployment: Vercel (frontend + API rewrites to
api.exploreyc.com) + Render (backend) + GitHub Actions (cron) - Key integrations: OpenAI (idea validation/embeddings), Perplexity AI (research), CoreSignal (company enrichment), Resend (email), Algolia (YC data source)
Development Commands
# Frontend dev server (proxies /api and /ws to localhost:8000)
cd frontend && npm install && npm run dev
# Backend dev server
cd backend && python3 -m venv venv && source venv/bin/activate && pip install -r requirements.txt && python3 -m uvicorn main:app --reload
# Production frontend build (from repo root)
npm run build
# Run backend tests (from backend/)
python -m pytest test_email_digest.py
python -m pytest test_pagination.py
No frontend test suite exists. Backend tests are integration-focused (test_*.py files in backend/).
Seeding local data: With DATABASE_URL unset the backend uses SQLite (backend/yc_companies.db, auto-created). Scrape YC data from the public Algolia API (no keys needed):
# Seed last 3 batches (with backend running)
curl -X POST http://localhost:8000/api/scrape \
-H "Content-Type: application/json" \
-d '{"batch": ["Winter 2025", "Summer 2024", "Winter 2024"], "hits_per_page": 1000, "max_pages": 20}'
# Check progress
curl http://localhost:8000/api/scrape/status/1
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.
- 4d ago First seen · 99 lines · 1,144 tokens per session scan A bea9647c95c4
exploreyc CLAUDE.md is an instructions file published in the GitHub repository KonstantinMB/exploreyc (41 stars, last pushed 1mo ago), licensed MIT. It adds 1,144 tokens to every session, about $0.0057 per session on Opus 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 2026-08-30.
Other instructions, from other repositories
opik python_sdk.instructions.md
Instructions for comet-ml/opik, covering opik python sdk code review guidelines, 🔧 core architecture principles, three-layer architecture, execution paths and 📋 api design standards.
opik copilot-instructions.md
Copilot instructions for comet-ml/opik, covering copilot code review instructions, project overview, 1. git workflow & branch management, branch naming convention and commit message standards.
opik AGENTS.md
AGENTS.md instructions for comet-ml/opik, covering repository guidelines, scope & inheritance, project structure & module organization, build, test, and development commands and coding style & naming conventions.
vellum-assistant AGENTS.md
AGENTS.md instructions for vellum-ai/vellum-assistant, covering vellum assistant — agent instructions, project structure, intellectual honesty, development and dependencies.
Patter AGENTS.md
Instructions for PatterAI/Patter, covering agents.md, non-negotiables (ci and reviewers block on these), before opening a pr, where things live and commits & prs.
legalise AGENTS.md
AGENTS.md instructions for b1rdmania/legalise, covering legalise — agent context (agents.md), 1. the one-paragraph version, 2. what it's built to answer (the four questions), 3. stack (boring by design) and 4. the core concepts.