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/mcp/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/mcp)<a href="https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/mcp"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/mcp/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/mcp"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/mcp.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 | $0.00000 | $0.02201 |
| Opus 5.5 | $0.00000 | $0.00880 |
| Sonnet 5.5 | $0.00000 | $0.00440 |
| Haiku 4.5 | $0.00000 | $0.00220 |
Grade B, and why
preview-env-mcp scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
1. `curl -sS -D - -o /tmp/preview-env-mcp-unauth.json -X POST "$BASE_URL/mcp" -H "content-type: application/json" -H "accept: application/json, text/event-stream" -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. `curl -sS -D - -o /tmp/preview-env-mcp-unauth.json -X POST "$BASE_URL/mcp" -H "content-type: application/json" -H "accept: application/json, text/event-stream" -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
preview-env mcp
{BASE_URL}/mcp. The product MCP exposes seven read tools (ADR-051): list_workspaces, search_knowledge, search_code, find_symbol, read_file, list_files, and get_related, plus the resource template ctxpipe://{org}/{workspace}/{+ref}. Each tool except list_workspaces needs an org slug argument. The server ignores ?orgSlug=. No tool runs a model or a chat turn. ctx_advisor is gone. Harness is PASS. HTTP/CLI plus a short browser task. Flow format: run-setup.
MCP-1 Discovery
Requires ONB-2. Steps
curl -sS -D - -o /tmp/preview-env-mcp-unauth.json -X POST "$BASE_URL/mcp" -H "content-type: application/json" -H "accept: application/json, text/event-stream" -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"preview-env","version":"0"}}}'.- GET
{BASE_URL}/.well-known/oauth-protected-resource/mcpand{BASE_URL}/.well-known/oauth-authorization-server.
Expect (UI) none.
Expect (backend) the unauthenticated POST is 401 (or 400 with a JSON-RPC auth error) with a WWW-Authenticate header naming oauth-protected-resource and scope="ctxpipe:read"; both well-known URLs return JSON with issuer and resource metadata; the metadata lists ctxpipe:read and ctxpipe:write in scopes_supported.
Budget 1 s / 3 s per request.
Evidence the response headers; x-request-id; trace.
MCP-2 Doctor
Requires MCP-1. Steps
npx ctxpipe doctor mcp --url "$BASE_URL/mcp"(reachability and OAuth metadata only; it does not list tools).
Expect (UI) none.
Expect (backend) exit code 0 with reachable plus metadata; a connection error is a FAIL. The output does not name ctx_advisor; where it points to a next step, it names the read tools (tools/list, list_workspaces, search_knowledge).
Budget 10 s / 30 s.
Evidence the command output.
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 · 0 tokens per session scan B a0a175300318
preview-env-mcp is a skill published in the GitHub repository ctxpipe-ai/ctxpipe (27 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,201 tokens. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). 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.