Borrowing it
Nothing to install: this file belongs to valory-xyz/olas-website. 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/valory-xyz/olas-website/main/CLAUDE.mdgit clone --depth 1 https://github.com/valory-xyz/olas-websiteWrote 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/valory-xyz/olas-website/claude-md)<a href="https://agentmods.dev/instructions/valory-xyz/olas-website/claude-md"><img src="https://agentmods.dev/badge/instructions/valory-xyz/olas-website/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/valory-xyz/olas-website/claude-md"><img src="https://agentmods.dev/badge/instructions/valory-xyz/olas-website/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 | $0.06279 | $0.06279 |
| Opus 5.5 | $0.02512 | $0.02512 |
| Sonnet 5.5 | $0.01256 | $0.01256 |
| Haiku 4.5 | $0.00628 | $0.00628 |
Grade A, and why
olas-website 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 yesterday.
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 — 214 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
This is the Olas Network marketing website — a Next.js 15 (Pages Router) application that showcases autonomous AI agents, staking programs, and the Olas protocol. The site uses Strapi as a headless CMS for editorial content, queries multi-chain GraphQL subgraphs for on-chain metrics, and persists those metrics as JSON snapshots in Vercel Blob storage that are refreshed by Vercel cron jobs.
Stack at a glance: Next.js 15 + React 19, Node 22, TypeScript-first (.ts/.tsx) with allowJs for legacy .js/.jsx, Tailwind CSS + shadcn/ui (Radix primitives), graphql-request, swr, @vercel/blob, viem, dayjs.
Development Commands
Use yarn for all commands (preferred in this repo):
yarn dev # Start dev server at http://localhost:3000
yarn build # Production build (postbuild runs next-sitemap)
yarn start # Start production server
yarn lint # ESLint
yarn lint:fix # ESLint with auto-fix
yarn lint:lockfile # Validate yarn.lock integrity (lockfile-lint)
Architecture
Directory Structure
pages/— Next.js Pages Router routespages/api/refresh-metrics/*.ts— cron-driven endpoints that fetch from subgraphs and write Vercel Blob snapshotspages/api/og/[[...slug]].tsx— dynamic Open Graph image generation (@vercel/og)pages/api/olas/[endpoint].ts— thin proxy toOLAS_API_URL(api.olas.autonolas.tech)pages/data/index.tsx— "Data Verification" page; documents the provenance/methodology behind published metrics (e.g.DailyActiveAgentsInfo,BabydegenMetricsInfo,MechGlobalsInfo)pages/card/index.tsx— shareable agent/card page- Dynamic routes use bracket notation:
[slug].tsx,[id].tsx,[[...slug]].tsx
components/— React components organized by page (e.g.,BuildPage/,AgentEconomies/,HomepageSection/,StakingPage/,PredictionAgentsTable/)components/ui/— Reusable UI primitives (shadcn/ui patterns over Radix)components/Layout/—Header,Footer,Menu,MenuMobile,PageWrapper,SectionWrapper, banners
common-util/— Shared utilities and business logiccommon-util/api/— Subgraph aggregation logic per category (main-metrics.ts,predict/,agent-economies/,other-metrics/) plusindex.tsfor Strapi calls (blogs, education articles)common-util/graphql/—client.ts(GraphQL clients per chain),queries.ts,types.ts(MetricWithStatus,WithMeta,SubgraphMeta),metric-utils.ts(lag detection / stale status helpers)common-util/snapshot-storage.ts— Vercel Blob save/get withmergeWithFallbacksemantics- Other helpers:
numberFormatter.ts,time.ts,web3.ts,charts.ts,og/,useFetchApi.ts,olasApr.ts,calculate7DayAverage.ts,indexers.ts(every subgraph/squid URL map, chain scope sentences,getSubgraphExplorerUrl)
data/— Static JSON:agents.json,chains.json,tokens.json,kits.json,useCases.json,resources.json, ABIs indata/ABIs/, etc.hooks/—usePersistentSWR,useWindowWidth,useHashlib/—utils.ts(only thecn()helper today)styles/— Global CSS and Tailwind layerspublic/— Static assets (fonts, images, OG images, documents)middleware.ts— Edge middleware (geo-blocking)vercel.json— Function limits + cron schedulesnext-sitemap.config.js— Adds/agents/<slug>paths fromdata/agents.json
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.
- yesterday Changed · +147 tokens per session 825a8a36ab46
- 1mo ago Changed · +2 lines · +409 tokens per session 1bc99b48ec00
- 1mo ago Changed · +2 lines · +147 tokens per session 1f90531e5510
- 1mo ago Changed · +1 lines · +252 tokens per session bc1d43a392b1
- 1mo ago Changed · +1 lines · +81 tokens per session 4110fe0427cf
- 1mo ago Changed · +3 tokens per session 2ae77cc83ecb
- 1mo ago Changed · +1 lines · +90 tokens per session 68400626d2c2
- 2mo ago First seen · 207 lines · 5,150 tokens per session scan A 63d495419db1
olas-website CLAUDE.md is an instructions file published in the GitHub repository valory-xyz/olas-website (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 6,279 tokens to every session, about $0.0251 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 2026-09-04.
olas-website CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| olas-website CLAUDE.mdvalory-xyz/olas-website | Instructions file | 2 | 2d ago | Apache-2.0 | A | 6,279 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |