Borrowing it
Nothing to install: this file belongs to weijt606/paris-ai-hackathon-2026. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/weijt606/paris-ai-hackathon-2026/main/CLAUDE.mdgit clone --depth 1 https://github.com/weijt606/paris-ai-hackathon-2026Wrote 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/weijt606/paris-ai-hackathon-2026/claude-md)<a href="https://agentmods.dev/instructions/weijt606/paris-ai-hackathon-2026/claude-md"><img src="https://agentmods.dev/badge/instructions/weijt606/paris-ai-hackathon-2026/claude-md/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/instructions/weijt606/paris-ai-hackathon-2026/claude-md"><img src="https://agentmods.dev/badge/instructions/weijt606/paris-ai-hackathon-2026/claude-md.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 | $0.01481 | $0.01481 |
| Opus 5 | $0.00740 | $0.00740 |
| Sonnet 5 | $0.00296 | $0.00296 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
paris-ai-hackathon-2026 CLAUDE.md 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 12d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Paris AI Hackathon 2026
This file is loaded into every Claude Code session in this repo.
Project context
- Event: Paris AI Hackathon 2026 — single-day sprint hosted by {Tech: Europe} + Hexa
- Format: ~7h coding window (10:45 → 17:30), Live demo at 18:00
- Chosen product: Wine intelligence — risk + market signals for Burgundy & Bordeaux, dual persona (vineyard | trade).
- Sponsors: OpenAI · Tavily · Pioneer.ai
- Architecture: Orchestrator agent (OpenAI Chat Completions tool-use loop) → weather/geo/tavily sub-agents → extraction_agent → dashboard. Pioneer.ai GLiNER2 classifier consumed via
classify()from extraction / feature agents. - Repo visibility: Shared with teammates AND hackathon organizers — never commit secrets or PII.
- Collab doc:
docs/AGENTS.md— architecture, file map, SubAgent contract. - Sponsor doc:
docs/SPONSORS.md— OpenAI / Tavily / Pioneer.ai usage + degradation ladder.
Stack
- Next.js 15 (App Router) + React 19 + TypeScript (strict)
- Tailwind v3
openaiSDK (Chat Completions tool-use orchestrator)- Tavily (public-web grounding, called via
fetch) - Pioneer.ai GLiNER2 inference API (called via
fetch) zodfor env + API validation- pnpm (
>=10), node>=20
No DB, no Vercel AI SDK, no shadcn — kept tight to what the agents actually need.
Sprint-day workflow
Pre-event:
pnpm installcp .env.example .env.local, fillOPENAI_API_KEY(required),TAVILY_API_KEY+PIONEER_API_KEY+PIONEER_MODEL_ID(optional)pnpm check:envto verify OpenAI actually pingspnpm devand confirm/api/healthreturns 200- Set
NEXT_PUBLIC_DEMO_MODE=trueand re-test/api/analyzeend-to-end on fixtures — this is the rehearsal fallback
On the day:
- Each sub-agent owner pulls latest, branches
agent/<name>, replaces stub body insrc/lib/agents/sub-agents/<name>.ts - Honor the SubAgent contract — orchestrator + types are off-limits
- Add a demo fixture branch for every new external call (H3)
- Feature freeze at T-1h before submission. Switch to demo-mode rehearsal.
- Live demo at 18:00 — practice the script ≥3 times.
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.
- 12d ago First seen · 133 lines · 1,481 tokens per session scan A e19a2db108db
paris-ai-hackathon-2026 CLAUDE.md is an instructions file published in the GitHub repository weijt606/paris-ai-hackathon-2026 (2 stars, last pushed 3mo ago), licensed MIT. It adds 1,481 tokens to every session, about $0.0074 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).