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 | $0.02351 |
| Opus 5.5 | $0.00014 | $0.00940 |
| Sonnet 5.5 | $0.00007 | $0.00470 |
| Haiku 4.5 | $0.00004 | $0.00235 |
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 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 — 205 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
Use explicit user requirements. An inferred or recommended default is a working
plan, not an explicit user requirement. For a small edit with clear requirements
to an existing deck, preserve the current stack, deck root, and visual system
except where the user requests a change, and proceed.
Inspect discoverable facts first: source material, the existing deck, the repo, a deployed URL, and project files. Ask only unresolved decisions that materially affect the result or scope. Do not re-ask a path, style, stage, stack, density, navigation, or delivery target the user already gave.
When the brief is still vague, treat alignment as focused grilling: purpose and
audience, content boundary and story, presentation format and density, then the
remaining execution constraints. Keep each round on the next highest-impact
unknown. Ask in normal chat text, with a recommended answer, rationale, and
impact. Group related low-risk questions when that reduces back-and-forth. Do
not call AskUserQuestion, AskQuestion, request_user_input, or any
structured single-choice, multiple-choice, or form-style prompt. Candidate
options may clarify a real directional choice, but they stay as plain text.
Cover these decisions at the level the task needs. This is a decision surface, not a confirmation ritual:
- Content plan: scope, non-goals, orientation, presentation format, duration, and content mix.
- Design plan: style, density, audit profile, motion direction, visual references, and whether a preview would reduce visual uncertainty.
- Project location plan: the
deck root, whether it is new, existing, inside a parent repo, an independent repo, or temporary, and which files are expected there. Use a path the user already gave or the existing deck's root. A user home directory or other broad workspace is not a reliable long-termdeck root. If a long-term deliverable has no reliable specified target, recommend one exact path and confirm before scaffolding. Do not scaffold into the current working directory just because the agent started there. - Build plan: fixed stage, navigation/touch expectations, technology stack, source material, and delivery target. Do not publish or deploy without authorization.
- Testing plan: test runner, test command, and required coverage across render, frame addressing, navigation, interaction isolation, layout safety, runtime errors, assets/fonts, and build/export/deployment checks. Testing is required for created or modified HTML slide artifacts; do not present it as a preference to confirm.
- Context document plan: where the Context document will live, when it will be updated, and whether the user wants a different location.
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 267 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 2.0 KB
- evals/10-animation-preference-gate.md 1.5 KB
- evals/11-slide-surface-boundary.md 1.5 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 980 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 21 KB
- references/02-design.md 15 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.
- 1mo ago Changed · -22 lines 259f4ad9bd81
- 1mo 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 (69 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 2,351 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
anti-slop-design
Autonomous Principal Design Technologist. Cures vibe-coded software from AI frontend slop using curated token archetypes and 7-axis quality gating.
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 $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
design-to-motion
Turns a static design (a Figma frame, dashboard, card set, app screen, or a UI on a photo background) into a pixel exact HTML replica that loads in from an empty state, then has every visual act out what it does (a chart being read, a list receiving items, a prompt being typed) in a seamless loop, and exports an MP4…
open-design-setup
Prepare or repair a project's prototyping environment so open-design can build prototypes with the project's own component library and render them through the project's toolchain. Use when the library target is needed and docs/design/prototyping.md is missing, stale, or failing; excludes HTML-only design work and…
edit-site
Plans, coordinates and customizes PAC CLI-downloaded Standard or Enhanced data model non-SPA Power Pages sites created from Microsoft templates or manually in Design Studio. Use for requests involving pages, localized content, navigation, assets, snippets, site markers, Liquid/web templates, page layouts, or styling.…