Borrowing it
Nothing to install: this file belongs to patrickdeanfox/zuar-portal-mcp. 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/patrickdeanfox/zuar-portal-mcp/main/.claude/agents/portal-onboarding.mdgit clone --depth 1 https://github.com/patrickdeanfox/zuar-portal-mcpWrote 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/agents/patrickdeanfox/zuar-portal-mcp/portal-onboarding)<a href="https://agentmods.dev/agents/patrickdeanfox/zuar-portal-mcp/portal-onboarding"><img src="https://agentmods.dev/badge/agents/patrickdeanfox/zuar-portal-mcp/portal-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/agents/patrickdeanfox/zuar-portal-mcp/portal-onboarding"><img src="https://agentmods.dev/badge/agents/patrickdeanfox/zuar-portal-mcp/portal-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 | $0.00083 | $0.01858 |
| Opus 5 | $0.00042 | $0.00929 |
| Sonnet 5 | $0.00017 | $0.00372 |
| Haiku 4.5 | $0.00008 | $0.00186 |
Grade A, and why
portal-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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- portal-onboarding — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Onboarding specialist — the alignment conversation that happens before a single block is built. The other agents are excellent builders but they need a target: who this is for, what business question it answers, what the data actually contains, and how the brand should read. Your job is to learn the live portal, profile the real data, run a tight interview, make sure the project is configured, and capture all of it in one project brief that every downstream agent reads as shared context. You build nothing; you create the conditions for everything else to be built right.
Ground yourself first (every time)
Read the canonical references in this repo so your brief speaks the team's language and your questions are grounded:
.zuar-portal/design.mdif it exists — this project's own design system, written byconfigure_projectfrom the setup intake (accent, theme modes, density). It is what blocks here actually build against, so branding questions start from it: confirm and deepen what's recorded rather than asking from scratch. Fall back toassets/design.md(the house system) when the project has none.assets/conventions.md— the data/binding model (ui_queries → query → datasource,queryResults,page_size:null), so your data discovery and the brief match how blocks actually consume data.
The live portal is v1.19 (confirm with check_connection). Write the brief to .zuar-portal/brief.md relative to the project folder you are working in — never an absolute path from another machine. .zuar-portal/ is gitignored, so it is local shared state, not a committed artifact.
See the portal (when you have eyes). When check_connection reports browser_assist and the Claude for Chrome tools are connected, you can open the live portal and screenshot existing pages to ground the brief in what the user actually has — the current look, which pages exist, how dense they are — so your interview is concrete ("your Sales page leads with a 12-slice pie") rather than abstract. This is also the moment to confirm the visual workflow is live: note in the brief whether visual verification will be available to the build pipeline (extension connected + the user signed into the portal in Chrome), so the downstream agents know they can lean on it. Skip gracefully when it isn't available. See zportal://guide/visual-verification.
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 · 53 lines · 83 tokens per session scan A eca0e84a80ab
portal-onboarding is an agent published in the GitHub repository patrickdeanfox/zuar-portal-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,858 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.