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 skills add nottelabs/notte-skills --skill migrate-to-nottegit clone --depth 1 https://github.com/nottelabs/notte-skillsWrote 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/nottelabs/notte-skills/migrate-to-notte)<a href="https://agentmods.dev/skills/nottelabs/notte-skills/migrate-to-notte"><img src="https://agentmods.dev/badge/skills/nottelabs/notte-skills/migrate-to-notte/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/skills/nottelabs/notte-skills/migrate-to-notte"><img src="https://agentmods.dev/badge/skills/nottelabs/notte-skills/migrate-to-notte.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00122 | $0.02601 |
| Opus 5 | $0.00061 | $0.01300 |
| Sonnet 5 | $0.00024 | $0.00520 |
| Haiku 4.5 | $0.00012 | $0.00260 |
Grade A, and why
migrate-to-notte 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 11d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migrate to Notte
This skill covers one funnel with two entry points:
- Track A — cost comparison only. A read-only, dated, evidence-backed decision brief. It does not modify code, credentials, billing, or provider resources. Run phases 0–3, then jump to §8 (external benchmark context) and §9 (decision brief).
- Track B — full migration. Everything in Track A, then a safe proof, an isolated build, validation, and a reversible handoff. Run phases 0–7, then §9.
Pick the track from the user's request. If they only asked what something would cost, run Track A and stop; offer Track B as the next step. If they asked to migrate, run Track B — a migration without a measured baseline is a rewrite, not a migration.
Use one disciplined process, then load only the reference for the provider discovered in the target. Do not combine providers or assume an API is equivalent because its name is similar.
0. Publish the execution plan — required first
Before tools, repository reads, or background work, post this plan in the main user-facing thread. Mark exactly one phase In progress and the rest Not started. This is a progress view, not an approval request unless blocked. Do not hide it in an internal tool.
For Track A (cost comparison):
| Phase | Outcome |
|---|---|
| 1. Notte setup | Quickstart, CLI, skills, and authenticated access verified. |
| 2. Provider/workflow inventory | Source, occurrences, workflows, and usage inventoried. |
| 3. Usage and pricing evidence | Verified prices plus a cost/concurrency model with low/base/high scenarios. |
| 4. Decision brief | Dated, evidence-backed comparison delivered. |
For Track B (migration):
| Phase | Outcome |
|---|---|
| 1. Notte setup | Quickstart, CLI, skills, and authenticated access verified. |
| 2. Discovery | Source docs, occurrences, workflows, and risks inventoried. |
| 3. Baseline | Usage, cost, latency, concurrency, and success evidence measured or bounded. |
| 4. Safe proof | A representative read-only Notte workflow is tested fairly. |
| 5. Isolated build | A progressive implementation and tests are built outside production. |
| 6. Validation | Static analysis, tests, review, and non-production evidence completed. |
| 7. Reversible handoff | Branch/PR, cleanup, rollout, rollback, and known gaps delivered. |
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 357 B
- references/anchorbrowser.md 1.1 KB
- references/browser-use-cloud.md 1.0 KB
- references/browserbase-stagehand.md 1.1 KB
- references/cost-model.md 2.2 KB
- references/hyperbrowser.md 1.1 KB
- references/kernel.md 1.1 KB
- references/measurement.md 968 B
- references/skyvern.md 1.3 KB
- references/steel.md 1013 B
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.
- 11d ago First seen · 231 lines · 122 tokens per session scan A eeb058b67161
migrate-to-notte is a skill published in the GitHub repository nottelabs/notte-skills (11 stars, last pushed 6d ago), licensed MIT. It adds 122 tokens to every session and 2,601 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
ego-browser
When you need a browser, read this Skill by default. Use it to open and operate websites, fill forms, click buttons, take screenshots, extract page data, sign in, and perform other browser automation tasks, as well as web app testing, dogfooding, QA, bug investigation, and app-quality review. ego-browser (ego-lite) is…
actionbook-web-test
Run browser-based web tests against websites using Actionbook CLI. Activate when the user wants to test a website workflow, run smoke tests, verify a user flow, check if a web application works, run regression tests, or validate browser-based interactions. Supports test definition, execution, assertion, reporting, and…
active-research
Deep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper, or technology. Enhanced with advanced browser automation — SPA handling, network idle wait, batch operations, stealth browsing, and intelligent page analysis. Use when user asks to research, analyze, investigate…
actionbook-scraper
Generate and verify web scraper scripts using Actionbook's verified selectors. Auto-validates generated scripts and fixes errors.
extract
Extract structured data from websites and produce an executable Playwright script plus extracted data. Use when the user wants to scrape, extract, pull, collect, or harvest data from any website — product listings, tables, search results, feeds, profiles, or any repeating content.
actionbook
Activate when the user needs to interact with any website — browser automation, web scraping, screenshots, form filling, UI testing, monitoring, or building AI agents. Provides pre-verified page actions with step-by-step instructions and tested selectors.