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/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/preview-env)<a href="https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/preview-env"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/preview-env/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/preview-env"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/preview-env.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 | $0.00082 | $0.01083 |
| Opus 5.5 | $0.00033 | $0.00433 |
| Sonnet 5.5 | $0.00016 | $0.00217 |
| Haiku 4.5 | $0.00008 | $0.00108 |
Grade A, and why
preview-env 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 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.
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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
preview-env
Browser + HTTP run of the critical flows against a disposable target: local host dev or a Railway PR preview. The product UI is driven through the backend origin; hosted MCP is {BASE_URL}/mcp?orgSlug={org}. This is not Storybook workspace-golden and not Playwright CI. The agent drives the browser from this catalogue on every run; there are no recorded scripts to replay.
Every run starts from registration: it creates its own accounts, organization, and Workspaces. There are no pre-seeded users. Never point a run at production.
1. Collect inputs
| Input | Example |
|---|---|
BASE_URL |
https://app.ctxpipe.localhost or https://backend-pr-280.up.railway.app |
mode |
local or preview, derived from BASE_URL in run-setup |
run-id |
UTC YYYYMMDD-HHMMSS, minted once per run |
GH_TEST_ORG |
ctxpipe-ai |
TEST_EMAIL_DOMAIN |
ctxpipe.dev unless the prompt names another; see run-setup |
local only: trace export |
the local-<name> environment from run-setup |
Optional: section (one or more area names); flags live-oauth, merge-pr, default-branch-write, restart-ok (each defined where it is used). Without a value for a required input, ask; do not invent one.
Run local before a preview of the same change.
Done when: every required input is a concrete string and the target guard passed.
2. Run setup and harness
Read run-setup.md (accounts, test data, flow format, evidence, human checkpoints), then complete harness.md (wake, canary).
Done when: harness is PASS. A harness FAIL is a blocker: stop and report only the harness.
3. Choose areas
| Prompt | Areas |
|---|---|
Full run / "run preview-env" / no section |
all, in suite order |
| One or several named areas | those areas, still in suite order |
Suite order: onboarding → auth → org-home → workspaces → hydrate → graph → chat → files-publish → connectors → mcp → resilience.
What ships with it
13 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.
- auth/SKILL.md 5.6 KB
- chat/SKILL.md 8.9 KB
- connectors/SKILL.md 7.6 KB
- files-publish/SKILL.md 7.6 KB
- graph/SKILL.md 2.6 KB
- harness.md 4.5 KB
- hydrate/SKILL.md 5.9 KB
- mcp/SKILL.md 7.7 KB
- onboarding/SKILL.md 5.8 KB
- org-home/SKILL.md 3.6 KB
- resilience/SKILL.md 3.9 KB
- run-setup.md 11 KB
- workspaces/SKILL.md 6.9 KB
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 · 80 lines · 82 tokens per session scan A a6d6258835fe
preview-env is a skill published in the GitHub repository ctxpipe-ai/ctxpipe (27 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 1,083 once invoked, about $0.0003 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…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
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.