Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add earlyaidopters/marks-pi-harness --skill editorial-webgit clone --depth 1 https://github.com/earlyaidopters/marks-pi-harnessWrote 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/earlyaidopters/marks-pi-harness/editorial-web)<a href="https://agentmods.dev/skills/earlyaidopters/marks-pi-harness/editorial-web"><img src="https://agentmods.dev/badge/skills/earlyaidopters/marks-pi-harness/editorial-web/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/earlyaidopters/marks-pi-harness/editorial-web"><img src="https://agentmods.dev/badge/skills/earlyaidopters/marks-pi-harness/editorial-web.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 | $0.00108 | $0.01613 |
| Opus 5 | $0.00054 | $0.00807 |
| Sonnet 5 | $0.00022 | $0.00323 |
| Haiku 4.5 | $0.00011 | $0.00161 |
Grade A, and why
editorial-web scanned grade A with 1 finding 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 9d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
5. **Verify with your eyes.** `npm run dev`, then `browser_check` with `expect` at scrollTo 0 (nav + serif hero + hero media frame), 0.3 (manifesto/features revealed, correct alternation), 0.6 (card rail + banner panel), How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Editorial websites
Build the class of site that looks like a printed magazine came alive: one expressive serif, soft paper canvas, media presented as rounded plates, calm confident motion. This genre wins on RESTRAINT — read references/editorial-anatomy.md first; it defines the two proven moods (soft-light product / warm editorial brand), the 10-section layout grammar, the motion grammar, and the instant-fail tells.
Routing: if the request needs WebGL, 3D, a game world, or scroll-driven video scrubbing, STOP and use the immersive-web skill. This skill is the no-WebGL editorial lane.
Pipeline (one shot)
Run on the LARGEST available model (the 122B). Set gates before starting:
/gate npm run build
/gate ! grep -rq '{{' index.html
/gate test -f DESIGN.md
Running non-interactively (no /gate available)? Then run those three commands yourself before declaring the build done, plus the CSS-markup contract check below. A failing check means the job is NOT done, no matter how good the screenshots look.
CSS-markup contract check (mandatory): every class selector you ADD to style.css must exist in index.html. A real 122B build wrote .banner__bg / .banner__overlay styles but never added those divs — the section silently rendered text-on-background-color with no image. After any CSS edit that introduces new class selectors, verify each one:
for cls in $(grep -o '^\.[a-z][a-z0-9_-]*' src/style.css | sort -u | tr -d '.'); do
grep -q "class=\"[^\"]*$cls" index.html || echo "MISSING IN HTML: .$cls"
done
Investigate every MISSING line (JS-created classes like .cursor-dot/.grain/.progress are the only legitimate misses).
- Start from the template (verified working — do not rebuild the machinery):
# do NOT mkdir the target first — cp creates it
cp -R ~/.pi/agent/skills/editorial-web/assets/template-editorial ./SITE_DIR && cd SITE_DIR
ls package.json # MUST exist here before continuing
npm install
README.md inside maps every file. The boot wiring in src/main.js (Lenis + ScrollTrigger single RAF, split-line reveals, drag rail) is correct — extend it, never re-derive it.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/template-editorial/index.html 4.7 KB
- assets/template-editorial/package.json 308 B
- assets/template-editorial/README.md 1004 B
- assets/template-editorial/src/main.js 3.8 KB runs code
- assets/template-editorial/src/style.css 8.9 KB
- references/editorial-anatomy.md 3.8 KB
- references/effects.md 8.2 KB
- references/variation.md 1.7 KB
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.
- 9d ago First seen · 74 lines · 108 tokens per session scan A 6f3bce0f8498
editorial-web is a skill published in the GitHub repository earlyaidopters/marks-pi-harness (11 stars, last pushed 29d ago), licensed MIT. It adds 108 tokens to every session and 1,613 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
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.