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 deepklarity/harness-kit --skill hk-mock-firstgit clone --depth 1 https://github.com/deepklarity/harness-kitWrote 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/deepklarity/harness-kit/hk-mock-first)<a href="https://agentmods.dev/skills/deepklarity/harness-kit/hk-mock-first"><img src="https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-mock-first/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/deepklarity/harness-kit/hk-mock-first"><img src="https://agentmods.dev/badge/skills/deepklarity/harness-kit/hk-mock-first.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 | $0.00126 | $0.03495 |
| Opus 5 | $0.00063 | $0.01747 |
| Sonnet 5 | $0.00025 | $0.00699 |
| Haiku 4.5 | $0.00013 | $0.00349 |
Grade A, and why
hk-mock-first 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 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.
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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hk-mock-first — Mock-First, Layer-by-Layer Feature Development
The traditional approach — build the plumbing, wire the API, then hope the UI works — inverts the feedback loop. You discover experience problems after committing to implementation choices. This skill inverts the flow: validate the experience first with realistic mocks, then progressively replace mocks with real code, one complexity layer at a time.
Why this matters: A feature that "works" but feels wrong is more expensive to fix than one that was never built. Mock-first means the human curates the experience before any plumbing exists. This directly serves the philosophy tenet of Taste as a Filter — the system produces options, the human filters. And Good Enough — you don't over-engineer layers that haven't been validated yet.
Context
<feature_context> $ARGUMENTS </feature_context>
If the context above is empty or unclear, ask the user:
- What feature or change are you building?
- Which user-facing interfaces does it touch? (UI pages, CLI output, API responses that drive UI)
- Where should the workspace live? (suggest
docs/mock-first/<feature-slug>/)
The Workspace
Everything lives on disk. The workspace is the product, not temp files — it's the organized record of what was mocked, what was accepted, and what's been deepened. It also serves as the resumption anchor: if the conversation compacts or a new session starts, the workspace contains everything needed to continue.
docs/mock-first/<feature-slug>/
├── tracker.md # Live state (the resumption anchor)
├── surface/
│ ├── interface-map.md # All user-facing interfaces this feature touches
│ ├── mock-data/ # Actual mock data files (JSON, fixtures, factories)
│ ├── mock-components/ # Mock UI components, stubs, or test pages (if applicable)
│ ├── states.md # All UI/interface states catalogued
│ └── acceptance.md # User's acceptance notes + screenshots
├── layer-1/
│ ├── boundary.md # What this layer is, where the complexity boundary sits
│ ├── test-plan.md # TDD: tests to write before implementation
│ ├── changes.md # What changed (files, diffs)
│ └── verification.md # Tests pass + interface still works
├── layer-2/
│ └── ...
└── summary.md # Written when feature ships (or when pausing long-term)
What ships with it
1 file 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.
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 · 342 lines · 126 tokens per session scan A 8da73f500881
hk-mock-first is a skill published in the GitHub repository deepklarity/harness-kit (96 stars, last pushed 1mo ago), licensed MIT. It adds 126 tokens to every session and 3,495 once invoked, about $0.0006 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
rails-frontend
Ruby on Rails frontend conventions — Hotwire, Turbo, Stimulus, views, components, assets. Use when implementing frontend features, building views, or working with JavaScript/CSS.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
web-verify
Look at your OWN front-end change before claiming it works -- navigate the loopback URL of a dev server or pod you started, screenshot the surface you changed, read the image to judge it, and embed it in chat. Three capture backends: playwright-cli (the session the dashboard Browser panel shows), the agent-browser CLI…
widgets
Render rich HTML inline via tags with theme-aware styling. Load when emitting an mcwidget so the iframe inherits the dashboard theme instead of clashing with light / dark / custom palettes.
neuron-structured-output
Design and implement structured output classes for Neuron AI agents using SchemaProperty attributes and validation rules. Use this skill when the user mentions structured output, JSON schema extraction, data validation, output classes, DTOs for AI responses, extracting structured data from LLM, or configuring property…