Sovereignty and session core: the prime/state-check/checkpoint skills, the standalone sovereignty guard hooks, and the session checkpoint system - a context-usage sensor, a threshold offer, a pre-compaction brief that states what the summary must keep verbatim, a redacted post-compact save, and a resume injector, all…
★not rated 2 8d agoA
tokens not measured
originalApache-2.0
Run Claude Code sessions, workers, and subagents on any model your subscriptions cover - one local proxy, zero API keys. Ships the /fabsol orchestrator + worker build flow.
★not rated 2 1mo agoA
tokens not measured
originalMIT
A set of tools for researching Chinese A-share stocks, including data retrieval, natural-language stock screening, holding analysis, and daily after-market routines. It is described as research software rather than financial advice.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Publish markdown to blogging platforms: Medium via the gist import flow, with a content-kit (style guide, banners, post naming) that keeps published content on-brand.
★not rated 2 1mo agoA
tokens not measured
originalMIT
A Chinese stock-market review tool that summarizes the day’s market conditions, the strength of a tracked investment theme, and possible breaches of your own holding rules.
★not rated 2 28d agoA
tokens not measured
originalMIT
Post a tweet or a linear thread (with optional image) to X from the terminal. Bring your own X app; OAuth2-PKCE bootstrap; dry-run cost preview; never auto-publishes. Also ships an MCP server with previewpost and publishpost tools for use directly inside Claude Code.
★not rated 2 29d agoA
tokens not measured
originalMIT
Validate whether a demand is real before you build it. Frame a falsifiable hypothesis, fan out parallel agents across two pillars (top-down: industry reports / market size / capital signals; bottom-up: Hacker News / App Store reviews / search & social), enforce a 7-axis demand scorecard with ≥2-source triangulation…
A DooTask plugin toolkit for creating plugins, preparing releases, improving project instructions, and making Conventional Commits. Conventional Commits are a standard format for describing Git changes.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Bob's Big Brain — the governed team brain: cited recall, hash-chained receipts. ONE plugin, two modes. Local (default): turn your own files into cited (qmd://) memory with deterministic governance and a tamper-evident SHA-256 hash-chained audit trail, in-process with no runtime network after one-time native dependency.
★not rated 2 5d agoA
tokens not measured
originalApache-2.0
17 Claude Skills for LinkedIn (post writing, hooks, carousels, niche and pillar strategy, content calendars, analytics) bundled with the Taplio MCP, so every skill runs on your real LinkedIn voice, audience, and numbers.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Build Godot 4 / GDScript game features with a team of AI agents — a dynamic, resumable Workflow pipeline with two unskippable gates (a rapid headless test gate and an 'is it fun' gate) that refuses to call a feature done until it's verified, capped by the Manager's thorough on-device final pass.
Provision, wire, and operate every service in your dev stack from Claude Code. Supabase, Neon, Vercel, Sentry, PostHog, OpenAI, Anthropic, GitHub, and more — one command each.
★not rated 2 2mo agoA
tokens not measured
originalMIT
Scientific TDD for AI coding agents: pre-registration before data, claims audit before submission, external novelty gate before desk reject, reproducibility check before claims. 16 skills + 8 subagents (7 qualitative reviewers + 1 computational traceability-auditor). Works on Claude Code, Cursor, Gemini CLI, Codex…
★not rated 2 4mo agoA
tokens not measured
originalMIT
Personal operator layer. /op:go routes any ask; /op:spec /op:plan /op:build run the scaled gate for features; /op:ship /op:sync /op:show /op:release run the daily ops. Every command ends with proof.
★not rated 2 2mo agoA
tokens not measured
originalMIT
SDLC framework for Claude Code: Hermes the Conductor, Argus the Monitor, expert personas, structured backlog, dashboard.
★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: