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 skills/valory-xyz/olas-website/run-devnpx skills add valory-xyz/olas-website --skill run-devgit 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/skills/valory-xyz/olas-website/run-dev)<a href="https://agentmods.dev/skills/valory-xyz/olas-website/run-dev"><img src="https://agentmods.dev/badge/skills/valory-xyz/olas-website/run-dev.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 | $0.00043 | $0.00953 |
| Opus 5 | $0.00022 | $0.00477 |
| Sonnet 5 | $0.00009 | $0.00191 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade C, and why
run-dev scanned grade C with 2 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
caches aggressively in dev. Fix: `rm -rf .next/cache/images`, then hard Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
for i in $(seq 1 60); do curl -sf http://localhost:<port> >/dev/null && break; sleep 1; done How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the olas-website dev server
Node/yarn setup (required first)
node/yarn are NOT on PATH in non-interactive shells — Node is managed by
nvm, which only initializes in interactive shells. Load nvm and let it resolve
the version from the repo's .nvmrc (single source of truth — nvm install
installs it if missing, otherwise just switches to it):
source "$HOME/.nvm/nvm.sh" && nvm install
yarn (classic, /usr/local/bin/yarn) works once node is on PATH.
Note: shell state does not persist between Bash tool calls — re-source nvm in
each call that needs node/yarn, or chain commands with && in one call.
Launch
yarn dev # run in background
- Next may not get port 3000 (it auto-falls back to 3001, 3002, …). Read the
actual port from the dev-server output line
- Local: http://localhost:<port>before navigating. If another process holds a port, it isn't ours — leave it. - Ready in ~3s. Poll, don't sleep — and note macOS has no
timeoutcommand:
for i in $(seq 1 60); do curl -sf http://localhost:<port> >/dev/null && break; sleep 1; done
.env.localexists in the repo root and is sufficient for local rendering. Homepage metrics come from Vercel Blob snapshots at build/ISR time, so pages render fine even if some subgraph env vars are missing.
Stop
lsof -ti:<port> -sTCP:LISTEN | xargs -r kill
Screenshots / driving the app
Pick a driver in this order:
chromium-cliif installed (which chromium-cli) — headless, no extension needed.- claude-in-chrome skill (Chrome extension MCP tools):
tabs_context_mcp→navigate→javascript_toolto scroll →computerscreenshot withsave_to_disk: true. There is no upfront check for the extension — invoking the skill is the check: it fails (or walks through setup) when the extension isn't installed/connected. If that happens, tell the user they can install it from https://claude.ai/chrome, and fall back to option 3 meanwhile. - Playwright fallback (no extension, no chromium-cli):
npx playwrightwith a one-off script —chromium.launch()→page.goto(devUrl)→page.screenshot(). First run downloads a browser (npx playwright install chromium), so prefer 1/2 when available.
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 · 89 lines · 43 tokens per session scan C 935acb62a6d2
run-dev is a skill published in the GitHub repository valory-xyz/olas-website (2 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 953 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
openchainbench-contributor
Walks a contributor through adding a new benchmark to OpenChainBench. Covers spec format, harness contract, Prometheus scrape wiring, local validation, and PR conventions.
rxdb-local-storage-only
Strict mandate that all local copy engine operations must use RxDB / IndexedDB substrate (LocalEngine / getRxDB) and avoid browser localStorage.
binance-square-scraper
用 browser-harness 抓取币安广场 (Binance Square) 热点话题、高讨论帖子、热搜币种，并生成带可点击跳转链接的 HTML 报告。.
binance-square-scraper
用 browser-harness 抓取币安广场 (Binance Square) 热点话题、高讨论帖子、热搜币种，并生成带可点击跳转链接的 HTML 报告。.
binance-square-scraper
用 browser-harness 抓取币安广场 (Binance Square) 热点话题、高讨论帖子、热搜币种，并生成带可点击跳转链接的 HTML 报告。.
playwright-best-practices
Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions…