Visual Design Mode overlay for annotating, inspecting, and modifying UI elements directly in the browser. Click elements to annotate, hover to inspect box models, and let Claude apply your design feedback to source code.
Police large volumes of AI-generated frontend work for design-system conformance, and audit the design system itself so it can be policed. Report-only: verdicts, reviews, plans, and issues — it never edits your code.
★not rated 8 27d agoA
tokens not measured
originalMIT
Zero-key Claude Code cost tracking, per project and per branch. Budget caps with SIGTERM enforcement, reads your local /.claude session logs, and syncs to a hosted team dashboard (Goei).
★not rated 8 yesterdayA
tokens not measured
originalMIT
The sovereign intelligence substrate — persistent memory, identity, and attested governance for your whole AI fleet across Claude Code, Cursor, Cline, Codex, Gemini CLI & Antigravity. Local-first. Forkable. Built on the Starlight Intelligence Protocol v1.1.1.
★not rated 8 todayA
tokens not measured
originalMIT
Full-lifecycle SDLC guardrailing framework for Claude Code — from product ideation and planning through implementation, code review, and test validation. Enterprise-grade skills and agents for AI-human peer collaboration.
★not rated 8 yesterdayA
tokens not measured
originalMIT
Free, open-source, headless alternative to Screen Studio: auto-zoom, idle speed-up, keystroke chips, smoothed cursor, text callouts, 9:16 vertical — from the CLI.
★not rated 8 2mo agoA
tokens not measured
originalMIT
Omakase-style skill discovery for Claude Code: the chef observes your work, finds matching skills in a federated catalog, and installs them after your approval. Bundles the Skill Suggester MCP server, the omakase-chef behavior skill, and three proactive hooks.
★not rated 8 yesterdayA
tokens not measured
originalMIT
Enforced code intelligence for Claude Code — an opinionated, LSP-backed command surface (grep, glob, sed, diagnostics) plus a hook that keeps the agent on the code-intelligent path.
★not rated 8 1mo agoA
tokens not measured
AGPL-3.0
Publish/share an artifact (HTML, Markdown, PDF, file, or whole site) as a private, branded, password-protected link on your own domain — from Claude. Zero-knowledge AES-256.
★not rated 8 2mo agoA
tokens not measured
originalMIT
Turn Claude into your F1 race engineer: 79 tools for live timing, telemetry, tyre strategy, pit stops, and every race since 1950 — plus a skill that explains it all in plain English.
★not rated 8 1mo agoA
tokens not measured
originalMIT
Adds intent-and-decision alignment before implementation with an optional durable HTML record, explicit behavior-preserving codebase cleanup, evidence-based review, PR explanations, UI design and mockups, clear explanatory visuals, and clear writing. Requires Node.js 22 or newer.
★not rated 8
changed 3d agoA
tokens not measured
originalMIT
The Agent Harness for Claude Code — Guardrails, Observability, and Quality Gates for AI-Powered Development. 15 specialist agents with structured workflows, budget controls, analytics, and self-learning.
★not rated 8 1mo agoA
tokens not measured
originalMIT
Canary for Claude Code and MCP clients: an Interactive Brokers daily brief, detailed regime and portfolio stress, account and position data, broker-reporting status, retrospective Edge review, rulebook checks, protection proposals, and option-exercise opportunities through the local canary CLI. The MCP tools are…
★not rated 8
changed 3d agoA
tokens not measured
originalMIT
Merit Aktiva accounting + Merit Palk payroll for Claude Code — full API coverage via the elnora-merit CLI, plus how-to skills for the correct Merit procedure: accounting (sales/purchase invoices, payments/bank reconciliation, VAT/KMD, reports, reverse charge) and payroll (employees & contracts, monthly…
★not rated 8 yesterdayA
tokens not measured
originalApache-2.0