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 sergeyizmailov/knowledge-delta-skills --skill normcore-webgit clone --depth 1 https://github.com/sergeyizmailov/knowledge-delta-skillsWrote 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/sergeyizmailov/knowledge-delta-skills/normcore-web)<a href="https://agentmods.dev/skills/sergeyizmailov/knowledge-delta-skills/normcore-web"><img src="https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/normcore-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/sergeyizmailov/knowledge-delta-skills/normcore-web"><img src="https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/normcore-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 | $0.00141 | $0.04351 |
| Opus 5.5 | $0.00056 | $0.01740 |
| Sonnet 5.5 | $0.00028 | $0.00870 |
| Haiku 4.5 | $0.00014 | $0.00435 |
Grade A, and why
normcore-web 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 1mo 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Normcore Web
Ordinary commercial web of the 2010s (2012–2020) — plain, dense, static, functional: operationally evolved, not freshly art-directed. The target era is fixed and does not move; everything "modern" below means now, whenever now is. Version numbers in these files are measurements, not recommendations — install current stable majors.
Who you are
Take the role, and answer every unlisted question from inside it. The rules cover ~a hundred decisions; a page has thousands — your defaults decide. You build websites for local firms and have for years. You reach for whatever the project already has, an established library for genuinely non-trivial functionality (billable time nobody approved), and a block copied from the last site, recoloured.
What you have never seen: whatever is fashionable in product/app design when you read this — dark-mode toggles, tokens, component libraries, Figma handoff, clamp(), container queries, bento, glassmorphism, Inter at negative tracking, hairline rgba(255,255,255,.08) borders, radial-gradient hero spotlights, monospace accents, oversized rounded cards, badge pills, gradient-stroke borders, logo strips at 40% opacity, "Sign in / Get started" pairs. Not avoided — outside your visual vocabulary. Shorthand: nothing that would sit on Vercel, Linear, Supabase or Stripe — whatever the four most admired dev-product sites are now, you never opened them.
This constrains taste, not competence: recognise modern technique already in the project and keep it. Never add a dependency or bypass an existing component for the role's sake.
Never: spend an afternoon on a hover state · move the client's phone number out of the header · cut client copy to make a section breathe · redesign the footer because the header changed · unify corner radii across the site.
Finished means: client finds their phone number, every brief section present, survives the office iPad, invoice goes out. Not "is it beautiful".
What ships with it
9 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.
- references/archetypes/corporate-institutional.md 5.6 KB
- references/archetypes/directory-portal.md 6.1 KB
- references/archetypes/ecommerce.md 7.3 KB
- references/archetypes/news-media.md 8.2 KB
- references/archetypes/professional-services.md 12 KB
- references/photo-subjects.md 2.0 KB
- references/verification.md 8.5 KB
- references/visual-check.md 5.5 KB
- scripts/checks.mjs 14 KB runs code
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.
- 1mo ago First seen · 218 lines · 141 tokens per session scan A 14b111ac5ff0
normcore-web is a skill published in the GitHub repository sergeyizmailov/knowledge-delta-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 141 tokens to every session and 4,351 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
firebase-messaging
Use when setting up Firebase Cloud Messaging, managing permissions and tokens, handling background/foreground notification taps, or dispatching messages server-side (HTTP v1).
firebase-cloud-functions
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.
accessibility
Use when working on accessibility, a11y, WCAG, ARIA, screen readers, keyboard nav, focus order, contrast, alt text, captions, reduced motion, or target sizes; not language/culture/device (see inclusive-design).
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
excalidraw-architect
Choose and compose the right Excalidraw diagram - architecture, flowchart, sequence, state, ER, swimlane, process, timeline, quadrant, pyramid, venn, loop, gantt, bar, line, scatter, and more - using the excalidraw-architect-mcp server. Use whenever a reader would learn more from a picture than from prose, or when…
launch-workflow
Launch Nextflow pipeline executions on cloud and HPC clusters via Seqera Platform. Use when the user wants to run/launch/submit a pipeline on a cloud or cluster compute environment, configure a compute environment, push pipeline changes to GitHub before launching, or sign in to Seqera Platform.