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 patrick-fu/awesome-skills --skill frontend-harness-slidesgit clone --depth 1 https://github.com/patrick-fu/awesome-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/patrick-fu/awesome-skills/frontend-harness-slides)<a href="https://agentmods.dev/skills/patrick-fu/awesome-skills/frontend-harness-slides"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/frontend-harness-slides/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/patrick-fu/awesome-skills/frontend-harness-slides"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/frontend-harness-slides.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.02578 |
| Opus 5 | $0.00018 | $0.01289 |
| Sonnet 5 | $0.00007 | $0.00516 |
| Haiku 4.5 | $0.00004 | $0.00258 |
Grade A, and why
frontend-harness-slides 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.
How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Harness Slides
Build HTML slides that survive iteration. This skill does not provide a starter project or require React, Vite, Tailwind, Playwright, or any other stack. Its unit is the harness contract: stable frame address, registry, fixed stage, frozen mode, audit surface, visual checks, and verified handoff.
PRE-BUILD ALIGNMENT HARD GATE
Before creating or modifying any HTML slide artifact, this is a hard gate. DO NOT create files, scaffold a project, write code, start a dev server, or begin implementation until the user has explicitly confirmed the Pre-Build Alignment in plain text.
Demand alignment is the first deliverable. Understand what the user is trying to accomplish, who will consume the deck, what the deck should include or exclude, and what outcome the presentation should drive. Walk the decision tree one branch at a time: purpose and audience, content boundary and story, presentation format and density, style and motion, then deck root, build, testing, and delivery. For each unresolved branch, ask a plain-text question with a recommended answer and rationale. If the answer can be found by reading source material, an existing deck, a repository, a deployed URL, or project files, inspect that source first and present the inference instead of asking a generic question. Keep each round focused on the next highest-impact decision; group low-risk execution confirmations only when that reduces back-and-forth without hiding uncertainty. Implementation begins only after the user confirms the final shared understanding.
Treat Pre-Build Alignment as focused, lightweight grilling-style alignment: explore discoverable facts first, challenge a vague brief when assumptions are unclear, expose the highest-impact tradeoffs, and keep moving toward a shared understanding the user can confirm. Do not turn the intake into a checklist dump or a form. Related low-risk confirmations can be grouped, but each key question still needs a recommended answer, rationale, and impact.
What ships with it
60 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.
- agents/openai.yaml 397 B
- evals/01-testing-plan-hard-gate.md 1.1 KB
- evals/02-registry-semantic.md 965 B
- evals/03-import-pptx-guidance.md 1.0 KB
- evals/04-stage-no-responsive-breakpoints.md 990 B
- evals/05-canvas-anti-pattern.md 712 B
- evals/06-humanizer-stop-slop-gate.md 875 B
- evals/07-editable-key-not-swallowed.md 1.1 KB
- evals/08-frozen-screenshot-determinism.md 939 B
- evals/09-vague-request-brief-intake.md 1.9 KB
- evals/10-animation-preference-gate.md 1.4 KB
- evals/11-slide-surface-boundary.md 1.4 KB
- evals/12-stable-frame-address-contract.md 1.0 KB
- evals/13-verify-and-ship-tier-and-artifact-hygiene.md 1.3 KB
- evals/14-multi-angle-test-gate.md 971 B
- evals/15-project-location-hard-gate.md 887 B
- evals/16-soft-grilling-alignment.md 1.3 KB
- LICENSE 1.0 KB
- README.md 74 KB
- README.zh-CN.md 72 KB
- references/01-plan.md 20 KB
- references/02-design.md 14 KB
- references/03-build.md 15 KB
- references/04-verify-and-ship.md 13 KB
- references/style/after-hours-luxe.md 5.9 KB
- references/style/analog-cutout-collage.md 5.6 KB
- references/style/annotated-source-and-diff.md 3.9 KB
- references/style/arcade-boss-fight.md 4.3 KB
- references/style/benchmark-matrix.md 3.6 KB
- references/style/blackboard-chalk-talk.md 4.4 KB
- references/style/botanical-specimen-plate.md 5.9 KB
- references/style/cassette-era-packaging.md 5.9 KB
- references/style/checklist-ledger.md 3.5 KB
- references/style/collaborative-pairing-board.md 3.9 KB
- references/style/context-bento-box.md 5.9 KB
- references/style/cyanotype-drafting-table.md 5.2 KB
- references/style/debug-reaction-board.md 3.8 KB
- references/style/decision-record.md 3.7 KB
- references/style/duotone-session.md 5.5 KB
- references/style/engineering-whiteboard-explainer.md 5.3 KB
- references/style/expedition-screenprint.md 5.5 KB
- references/style/field-notes-report.md 3.8 KB
- references/style/front-page-broadsheet.md 5.4 KB
- references/style/index.md 34 KB
- references/style/interactive-dialogue-stage.md 4.6 KB
- references/style/kinetic-type-punchline.md 4.3 KB
- references/style/kitchen-prep-station.md 3.8 KB
- references/style/liquid-glass.md 5.5 KB
- references/style/machine-age-deco.md 5.3 KB
- references/style/magazine-masthead.md 6.2 KB
- references/style/maintainer-issue-brief.md 3.8 KB
- references/style/mechanical-scoring-funnel.md 4.0 KB
- references/style/mid-century-grove.md 5.5 KB
- references/style/minimal-product-keynote.md 6.1 KB
- references/style/neo-brutalist-bulletin.md 6.1 KB
- references/style/object-metaphor-hero.md 4.4 KB
- references/style/objective-swiss-grid.md 5.6 KB
- references/style/operating-manual.md 3.7 KB
- references/style/red-wedge-agitprop.md 5.5 KB
- references/style/research-memo.md 4.1 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.
- 11d ago First seen · 227 lines · 36 tokens per session scan A c4999fca6891
frontend-harness-slides is a skill published in the GitHub repository patrick-fu/awesome-skills (58 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 2,578 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
webgl-liquid-metal
A real-time liquid-metal shader — a domain-warped noise field shaded as molten chrome, with a sweeping specular highlight over an iridescent thin-film (cosine-palette) sheen. No textures. Rendered as a single self-contained index.html. Use when the brief asks for "liquid metal", "molten chrome", "iridescent"…
webgl-neon-grid
A real-time synthwave scene — a perspective floor grid scrolling toward a banded retro sun under a neon starfield, all from one fragment shader. No textures. Rendered as a single self-contained index.html. Use when the brief asks for "synthwave", "outrun", "retro 80s", "neon grid", "perspective grid", "vaporwave", or…
webgl-particle-galaxy
A real-time particle galaxy — tens of thousands of additive-blended GPU points spiraling around a bright core, their orbits solved entirely in the vertex shader (from glVertexID), so the whole cloud draws in one call. Rendered as a single self-contained index.html. Use when the brief asks for a "particle field"…
webgl-depth-gallery
A scroll-reactive 3D image gallery in Three.js: Z-stacked images crossfade over per-image mood backgrounds with velocity breath, a glowing cursor trail and an editorial CMYK/RGB/HEX/PMS color card.
webgl-distortion-grain
A vertical gallery (Three.js) where planes bend with scroll velocity, ripple under the cursor via simplex noise, and carry a film grain.
webgl-horizontal-parallax
A horizontal-scroll WebGL gallery (Three.js): frames glide sideways with lerp smoothing and each image parallaxes its texture (UV shift) by its position in the viewport.