The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Niblet Skill MCP
MCP server and design skill that grounds coding-agent UI work in real product screens. Two tools, npx-installable.
Install
claude mcp add niblet -- npx -y @pymodel/nibletInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →Real screen references and a design skill, for coding agents that build UI.
→
→
By elkaix for PyModel
A coding agent building UI gets two things here: a design skill that keeps it working from your product rather than a generic template, and real screen references from the Niblet catalogue when a specific visual question is still open.
The skill settles the screen's job, its real states, and what counts as done before writing anything; it builds from the tokens and components already in your codebase; and it finishes by rendering the surface and exercising it, so a green build alone is not a pass.
The skill works alone. The server is optional and needs a token.
Install the skill
npx skills add PyModel/niblet-skill-mcp --skill niblet -y
Or copy it yourself, keeping references/, agents/, LICENSE, and NOTICE alongside it:
cp -r skill/niblet ~/.claude/skills/niblet # Claude Code
cp -r skill/niblet ~/.pi/agent/skills/niblet # Pi (its skills CLI has no -g for this target yet)
cp -r skill/niblet ~/.agents/skills/niblet # agents that read ~/.agents/skills
Then ask for it by name:
Use Niblet to design the checkout empty and error states.
The workflow settles the screen's job, primary action, hierarchy, existing tokens, real states, and acceptance criteria before writing anything. It finishes by rendering the surface and exercising it, so a green build on its own does not count as a pass.
Connect the server
Pick one. For public catalogue access, use hosted MCP with the niblet_at_… account key created at niblet.pymodel.com/account:
claude mcp add --transport http niblet https://niblet-api.pymodel.com/mcp \
--header "Authorization: Bearer $NIBLET_ACCOUNT_KEY"
For Claude Desktop, claude.ai, or Claude mobile, which cannot send a key header, add hosted MCP as a custom connector and sign in instead: Settings → Connectors → Add custom connector → https://niblet-api.pymodel.com/mcp, then sign in to Niblet and allow access. No key is involved; revoke the grant any time under Connected apps at niblet.pymodel.com/account. Step-by-step screenshots: niblet.pymodel.com/docs#claude.
For the token-free bundled skill resources, niblet_help, and niblet_status, run the local stdio adapter:
claude mcp add niblet -- npx -y @pymodel/niblet
Or use the equivalent host configuration:
{
"mcpServers": {
"niblet": {
"command": "npx",
"args": ["-y", "@pymodel/niblet"]
}
}
}
The local adapter's three catalogue tools call REST /v1, not hosted MCP. Public niblet_at_… account keys created at niblet.pymodel.com/account authorize both /v1 and /mcp. Set NIBLET_TOKEN to that key, plus NIBLET_API_ORIGIN and NIBLET_MEDIA_ORIGIN only when targeting a self-hosted deployment. Skill resources, niblet_help, and niblet_status configuration remain available with no token.
Similar plugs
Reverse engineer anything with agents, from app behavior down to native binaries.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype…
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io