Borrowing it
Nothing to install: this file belongs to ctxpipe-ai/ctxpipe. 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/ctxpipe-ai/ctxpipe/main/.agents/skills/preview-env/onboarding/SKILL.mdgit clone --depth 1 https://github.com/ctxpipe-ai/ctxpipeWrote 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/ctxpipe-ai/ctxpipe/onboarding)<a href="https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/onboarding"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/onboarding/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/ctxpipe-ai/ctxpipe/onboarding"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/onboarding.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 | $0.00027 | $0.01569 |
| Opus 5.5 | $0.00011 | $0.00628 |
| Sonnet 5.5 | $0.00005 | $0.00314 |
| Haiku 4.5 | $0.00003 | $0.00157 |
Grade A, and why
preview-env-onboarding 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 3d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
preview-env onboarding
First area of every run. Creates account A, the org, the GitHub connection, and Workspace 1; every later area reads them from the run state. Harness is PASS. Flow format: run-setup.
ONB-1 Register a fresh account
Requires account A credentials from run-setup; sign-up page open (harness step 3). Steps
- On
{BASE_URL}/.auth/sign-up, submit account A's email and password (and a name if the form asks). - Observe where the browser lands.
Expect (UI)
- The browser reaches
/onboarding(a user with no org is redirected there from/) and the first slide, Welcome to ctxpipe, shows Next. - Uncertain: the sign-up form may route to
/.auth/email-verification("check your email") although no verification is required. If so, sign in with the same credentials and record the screen as an observation, not a FAIL.
Expect (backend) users row for A with onboardingCompletedAt empty; a credential row in accounts; a sessions row.
Budget 3 s / 10 s, submit to onboarding visible.
Evidence ONB-1-1.png (form), ONB-1-2.png (welcome slide); trace of the sign-up request.
ONB-2 Create the org and land on Home
Requires ONB-1. Steps
- Click Next on Welcome to ctxpipe.
- On Create your organization, first submit a 33-character slug and read the error; then enter name
preview-env {run-id}and slugpe-{YYYYMMDDHHMMSS}and submit (Enter or the create button). - Observe where the browser lands. ONB-3 connects GitHub from the guide.
Expect (UI) two slides (welcome, create-org) and no Connect GitHub slide; the 33-character slug shows an inline validation error and creates nothing. After the org is created, the browser lands on Home (/{orgSlug}). Home fades in one time when its data is ready, with no layout shift. The Get started guide shows 0 of 6 done with Connect GitHub as the open row, and the Activity region below it is empty (No commits on the default branch yet.).
Expect (backend) organizations row with the slug; members row for A with the owner role; A's active organization set; users.onboardingCompletedAt set for A; org_onboarding row for the org.
Budget 3 s / 10 s, submit to Home visible.
Evidence ONB-2-1.png (validation error), ONB-2-2.png (Home with the guide); trace of the org-create request and the two onboarding-complete requests.
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.
- 3d ago Changed d3bad555f45b
- 4d ago First seen · 68 lines · 27 tokens per session scan A bd6db601b2b0
preview-env-onboarding is a skill published in the GitHub repository ctxpipe-ai/ctxpipe (27 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,569 once invoked, about $0.0001 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 2026-10-21.
Other skills, from other repositories
browser-journey-test
Validate user stories by simulating real user journeys in a live browser against deployed application. Activate after implementation to verify actual user experience against acceptance criteria, not just code logic.
sidekick-audit
Deterministic UI quality audit of a web page or a whole product — WCAG 2.2 A/AA accessibility (axe-core), Core Web Vitals (LCP/CLS), browser health (console errors, failed requests, mixed content) and tap-target size — reported dimensions-first, with confirmed-vs-uncertain findings clustered into root-cause families…
sidekick-test
Goal-based end-to-end UI testing that PROVES the outcome. Given a URL and a plain-language goal (e.g. 'sign up, create a project, and invite a teammate'), sidekick drives a real browser to do it and then verifies success with a DETERMINISTIC signal on the real page — the execution agent is never allowed to grade its…
tdd
Enforces red-green-refactor TDD cycle with atomic commits per phase. Used when implementing features, fixing bugs, or when tests should drive the design.
agent-evaluation
A guide to measuring whether an AI agent works reliably on the tasks that matter. It covers repeatable test environments, program checks, human-like scoring rules, failure analysis, and experiments that separate model problems from system problems.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.