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/org-home/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/org-home)<a href="https://agentmods.dev/skills/ctxpipe-ai/ctxpipe/org-home"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/org-home/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/org-home"><img src="https://agentmods.dev/badge/skills/ctxpipe-ai/ctxpipe/org-home.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 | $0.00023 | $0.00985 |
| Opus 5.5 | $0.00009 | $0.00394 |
| Sonnet 5.5 | $0.00005 | $0.00197 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
preview-env-org-home 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
preview-env org-home
Shell and Home for the run's org. Harness is PASS; onboarding created the org and Workspace 1. Flow format: run-setup. Home is /{orgSlug}/ (a page); sign-in lands on a Workspace composer, not Home.
HOME-1 SideNav regions
Requires ONB-4. Steps
- On
/{orgSlug}/or a Workspace, expand the rail if collapsed.
Expect (UI) visible: Home, Search (⌘K), Connectors, a Workspaces label with a + button (aria-label "Add Workspace") and Workspace rows, the organization switcher, and the account control. No org-wide Chat, Repositories, or Knowledge graph entries.
Expect (backend) none.
Budget 3 s / 10 s, navigation to rail visible.
Evidence HOME-1-1.png.
HOME-2 Home dashboard
Requires ONB-4. Steps
- Open Home (
/{orgSlug}/, no extra segment).
Expect (UI) a Workspace picker (aria-label "Select workspace") showing Workspace 1, the composer (placeholder What should ctxpipe do in this Workspace?), and the activity region (heatmap and recent commits, or No commits on the default branch yet.). In an org with no Workspace, the Get started guide (or, after the guide, a Create Workspace button) takes the composer's place, and the activity region shows empty.
Expect (backend) GET /{orgSlug}/api/v1/workspaces/{slug}/activity returns 200.
Budget 3 s / 10 s, navigation to composer visible.
Evidence HOME-2-1.png; trace of the activity request.
HOME-3 Send from Home opens a conversation
Requires HOME-2; hydrate need not be ready (the answer is timed in CHAT-1). Steps
- On Home, pick Workspace 1, type a real question about its repository, and send.
Expect (UI) the URL becomes /{orgSlug}/ws/{workspace1Slug}/conv_… immediately; the user bubble is shown with Setting up sandbox or Thinking…; the sidebar lists the conversation as New conversation, then a model-written title after the first turn.
Expect (backend) conversations row (source ui) for the Workspace; chat_threads row; first message in conversation_messages after the turn.
Budget 1 s / 2 s, Send to the URL containing conv_.
Evidence HOME-3-1.png; the new conversation id; trace of the conversation-create request.
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 · 67 lines · 23 tokens per session scan A 62ffb6bda4d8
preview-env-org-home is a skill published in the GitHub repository ctxpipe-ai/ctxpipe (27 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 985 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
evidence-publish
Deliver a QA/evidence packet to a tracker or keep it local, behind an always-ask preview gate. Protocol for /orc:qa Phase 6, /orc:evidence, and any evidence-delivery step.
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…
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.