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 agentmods add skills/morphicai/harness-fe/skillnpx skills add Morphicai/harness-fe --skill skillgit clone --depth 1 https://github.com/Morphicai/harness-feWhat 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 | $0.00079 | $0.08973 |
| Opus 5 | $0.00039 | $0.04487 |
| Sonnet 5 | $0.00016 | $0.01795 |
| Haiku 4.5 | $0.00008 | $0.00897 |
Grade A, and why
harness-fe 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 2d 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 — 566 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness-FE Agent Skill
You have direct access to a running frontend app via the harness-fe MCP daemon. The daemon bridges your tools to (1) the build plugin (source intelligence) and (2) the browser tab (live DOM, console, network, rrweb recording).
Tool names use underscores. Every tool is
mcp__<server>__<name>with underscores throughout —project_list,session_summary,page_click. The server prefix depends on the user's MCP config (commonlyharness-fefor the shared gateway,harness-solofor the loopback daemon). This doc writes the bare name (project_list); prepend whichever prefix your environment exposes.
Setup — do this first if the project isn't wired up
Before any tool will return data, the host project needs two things: a build-time
plugin (or jsxImportSource) and an MCP daemon entry in the agent's config. Pick
the integration path that matches the project:
Vite (React / Vue) — most common
pnpm add -D @harness-fe/vite @harness-fe/runtime- Add to
vite.config.ts:import { harnessFE } from '@harness-fe/vite'; export default defineConfig({ plugins: [react(), harnessFE()] }); - Register the daemon in
.mcp.json(or the equivalent agent config):{ "mcpServers": { "harness-fe": { "command": "npx", "args": ["@harness-fe/mcp-server", "--stdio"] } } }
Next.js (App or Pages Router) — supports SSR session continuity:
pnpm add -D @harness-fe/next @harness-fe/react-jsx @harness-fe/runtime @harness-fe/node-runtimetsconfig.json:"compilerOptions": { "jsxImportSource": "@harness-fe/react-jsx" }next.config.mjs:export default withHarness(config, { projectId: '<app-name>' })app/layout.tsx: render<HarnessScript />inside<body>- Same MCP daemon config as above.
Webpack / Rspack / other React toolchains: use @harness-fe/webpack or
@harness-fe/unplugin; the rest is identical.
After setup, run npx @harness-fe/mcp-server once (or it auto-spawns via the
agent's stdio config) and start the dev server. tab_list should return at
least one tab — you're wired up.
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.
- 2d ago First seen · 566 lines · 79 tokens per session scan A ef7ce05f87e9
harness-fe is a skill published in the GitHub repository Morphicai/harness-fe (2 stars, last pushed 13d ago), licensed MIT. It adds 79 tokens to every session and 8,973 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
hierarchy-check
Visual hierarchy and information architecture analysis.
spacing-audit
Spacing consistency and grid adherence analysis.
typography-audit
Typography quality and scale analysis.
color-harmony
Color palette quality and consistency analysis.
responsive-check
Basic responsive design checks.
accessibility
WCAG 2.1 AA compliance audit.