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/skills/portal-118-migration/SKILL.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/skills/patrickdeanfox/zuar-portal-mcp/portal-118-migration)<a href="https://agentmods.dev/skills/patrickdeanfox/zuar-portal-mcp/portal-118-migration"><img src="https://agentmods.dev/badge/skills/patrickdeanfox/zuar-portal-mcp/portal-118-migration/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/patrickdeanfox/zuar-portal-mcp/portal-118-migration"><img src="https://agentmods.dev/badge/skills/patrickdeanfox/zuar-portal-mcp/portal-118-migration.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 | $0.00092 | $0.05573 |
| Opus 5 | $0.00046 | $0.02787 |
| Sonnet 5 | $0.00018 | $0.01115 |
| Haiku 4.5 | $0.00009 | $0.00557 |
Grade A, and why
portal-118-migration 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 12d 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 — 401 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portal 1.18 block migration
Migrates a block's data-access layer from the pre-1.18 async-fetch pattern to the 1.18+ synchronous queryResults pattern. The portal now injects data before the block script runs — no fetch needed. The block just reads currentBlock.queryResults[n].mappedData and renders.
Portal-WIDE migration? Use the playbook + tools first
This skill converts ONE block. For a whole-portal version migration, wrap it in the universal method (zportal://guide/migration-playbook, or /portal-migrate):
- The
migration_kickoffMCP prompt (a prompt, not a tool) — settle scope once, up front: native chart widgets (convert/repair/leave — ask the user), test/QA pages, hardcoded-origin fixes, cadence, rollback home. Record the answers to.zuar-portal/migration-scope.jsonbefore the preflight. migration_preflight— the empirical audit. Scope by FUNCTION, not code: native/config-driven widgets and template blocks break with zero migratable script; every code-bearing field is scanned (comment/string-only matches are labeled — don't scope off them); placement runs through layouts AND partials AND snippets; every bound query is executed (failures, missing/stale column metadata →repair_query_metadata, numeric-as-string columns).snapshot_portal— requirecomplete: truebefore the first write.- Probe the target build in a browser (the preflight's
browser_probes) — every doc/skill statement about runtime behavior, including this skill's, is a hypothesis until verified on the target build. Then validate the full pattern on ONE canary block end-to-end before batch-applying. - Convert in minimal-diff batches, round-trip verifying every write.
update_blockgrandfathers pre-existing rule violations (flags, doesn't block); preview withvalidate_block { against_block_id }.
What changed in 1.18
| Concern | Pre-1.18 (legacy) | 1.18+ (current) |
|---|---|---|
| Data access | await zPortal.dataSource.fetchResults(...) inside the block |
currentBlock.queryResults[n].mappedData — synchronous, already populated |
| Loaded callback | Called after async fetch resolves | Called in finally after synchronous render — block MUST call it or the page loader hangs |
| Re-render trigger | zPortal.dataSource.on('load', dsId, handler) |
Same — still works; portal re-runs the block script on filter change |
QUERY_INDEX |
None — single implicit fetch | Declare const QUERY_INDEX = { name: 0, ... } to document which ui_queries slot is which |
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.
- 12d ago First seen · 401 lines · 92 tokens per session scan A 0be408ee2548
portal-118-migration is a skill published in the GitHub repository patrickdeanfox/zuar-portal-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 5,573 once invoked, about $0.0005 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 skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…