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-block-pipeline/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-block-pipeline)<a href="https://agentmods.dev/skills/patrickdeanfox/zuar-portal-mcp/portal-block-pipeline"><img src="https://agentmods.dev/badge/skills/patrickdeanfox/zuar-portal-mcp/portal-block-pipeline/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-block-pipeline"><img src="https://agentmods.dev/badge/skills/patrickdeanfox/zuar-portal-mcp/portal-block-pipeline.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 | $0.00071 | $0.01239 |
| Opus 5 | $0.00036 | $0.00620 |
| Sonnet 5 | $0.00014 | $0.00248 |
| Haiku 4.5 | $0.00007 | $0.00124 |
Grade A, and why
portal-block-pipeline 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portal block pipeline (repo orchestration)
Blocks are never created raw. A spec flows through gated specialist stages, each one
an agent in .claude/agents/. This skill is the thin orchestration map; the how of
block authoring lives in the global skills — load zportal (zPortal API + the two-field
block structure), currentblock (currentBlock.queryResults data access), and
decompose-html-to-zportal-blocks (splitting a monolith into blocks) — and the enforced
rules in assets/conventions.md + house style in assets/design.md. Do not work from
memory; read those.
The gated pipeline
spec → builder → stylist → responsive → debugger → adversary → advisor → ship
(build) (polish) (mobile) (fix bugs) (break it) (align)
Run it via the /portal-build command (.claude/commands/portal-build.md) for one block,
or the .claude/workflows/portal-block-pipeline.js workflow for a hands-off run that loops
automatically. Drive each stage with the Task tool and pass the previous stage's output
(the block_id + its notes) into the next — stages share state through that handoff, not
through re-discovery.
Stage roles + output contract
| Stage | Agent | Does | Hands off |
|---|---|---|---|
| Build | portal-block-builder |
discovers data, verifies real columns, authors the two fields, binds via ui_queries, validates, creates |
block_id, bound query_id/datasource, exact column aliases, fallbacks/async paths, open questions |
| Style | portal-block-stylist |
applies assets/design.md — hierarchy, color, type, spacing, elevation. CSS + structure only; never touches JS logic or the binding |
restyled block_id, design decisions |
| Responsive | portal-responsive-specialist |
breakpoints, fluid grids, ≥44px touch targets, no overflow (see the portal-responsive skill) |
breakpoints handled, residual width risks |
| Debug | portal-block-debugger |
fixes runtime footguns: the $ trap, AMD/window.define race, queryResults shape, dropped :root tokens, missing loaded-callback, re-render leaks |
fixes applied, anything still suspect |
| Adversary | portal-block-adversary |
read-only gate — red-teams for silent-data traps + edge cases, with evidence | findings list (severity + blocking) and a ship / needs-fixes verdict |
| Advisor | portal-block-advisor |
read-only — does it serve the business question, the user, the data? | substance/UX recommendations |
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 · 75 lines · 71 tokens per session scan A 7dfd22ceb331
portal-block-pipeline is a skill published in the GitHub repository patrickdeanfox/zuar-portal-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,239 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 skills, from other repositories
image-compare
Compare two image files on disk and report what changed, region by region. Trigger on "what changed between these two images", "diff these PNGs", "did this render drift", "compare screenshots/exports/renders".
Cypress v14 Component Testing
Component testing patterns with Cypress v14 including React, Vue, and Angular component mounting, custom mount commands, interaction testing, visual snapshots, and integration with Vite and Webpack bundlers.
visual-qa-testing
Visually QA a web application by launching it in Cursor's built-in browser, taking screenshots, checking console errors, and auditing network requests. Use after making UI changes to verify they look correct.
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
review-screenshot
A standard workflow for taking screenshots to check a user interface, using a dedicated review process for different verification modes.
visual-regression-lab
Compare captures; stitch lazy/animated pages.