WhatsApp channel for Claude Code — messaging bridge via WhatsApp Web with built-in access control. Manage pairing, allowlists, and policy via /whatsapp:access.
★not rated 2 7mo agoA
tokens not measured
originalMIT
Research-first workflow for building modern, accessible frontend UI components in the spirit of Wes Bos. Researches pitfalls and platform capabilities before planning, designs for WCAG accessibility with modern web standards, then verifies the approach against Wes Bos on X plus trusted sources (MDN, web.dev…
Keeps a project's noise out of Claude's default context: audit-context measures where the budget is going, ignore-setup applies a managed .ignore, a Glob setting, and a short read-deny list for secrets, leaving every excluded path readable on purpose.
★not rated 2 yesterdayA
tokens not measured
originalMIT
A design system for documents: evidence-led analytical reports, diagrams, charts, decks, and thirty-four prose presets across eleven reading patterns — composed from a pattern's modules when no preset fits — plus guided brand theming, all sharing one semantic token contract. Writing lands as Markdown by default…
Palambur Method · asks the decisive questions before producing a business document (job advert, quote, payment reminder, contract, internal memo), then returns the completed Palambur Template and the final deliverable. Swiss safeguards (Gender Equality Act, Data Protection Act, Code of Obligations, Labour Act), data…
★not rated 2
changed 1mo agoA
tokens not measured
originalMIT
Persistent project memory for Claude Code — indexes your repo into local JSONL and auto-injects task-relevant context (BM25, no LLM calls, nothing leaves your machine).
★not rated 2 18d agoA
tokens not measured
originalApache-2.0
Multi-agent code review that fans out to specialized subagents (bugs, security, CLAUDE.md compliance, git history, test coverage), scores findings by confidence, filters noise, and reports to the terminal or as inline GitHub PR comments.
Real-time collaboration between two Claude Code sessions over a shared IRC channel: a built-in chat hub, self-naming peers, and automatic message delivery via hooks.
★not rated 2 4mo agoA
tokens not measured
originalMIT
Continuous memory that survives context compaction — harvests your agent's own confidence-marked claims into a verbatim brief and re-injects it after compaction.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Instinct Engine that scans recent sessions, journals, and decisions for recurring patterns and turns them into concrete captures (rules, concept notes, writing seeds, skill improvements). Detects what's hardening into real insight before it evaporates.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Install the WireBoard tracking script and custom events (declarative or programmatic) in any codebase, or via the official Google Tag Manager template.
★not rated 2 5mo agoA
tokens not measured
originalMIT
A communication layer for your AI coding agent: plain language, no jargon, no invented timelines, and one clear yes before anything irreversible — shaping how the agent talks to you, not how it works.
★not rated 2
changed 1mo agoA
tokens not measured
originalMIT
AI article engine for WordPress: research, write, and optimize SEO + GEO content, then publish via the WordPress REST API. 7 skills + 8 commands for Claude Code.
★not rated 2 5mo agoA
tokens not measured
originalMIT
Specialized skills and research agents for astronomy literature, inference, visualization, and scientific software engineering.
★not rated 2 3mo agoA
tokens not measured
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: