A tiny phase gate for coding agents: your shell checks decide pass/fail (never the LLM), your workflow routes the agent (advance / retry / escalate / done). The agent drives, headsign holds the state.
★not rated 1
changed 6d agoA
tokens not measured
originalMIT
Paste an Instagram, TikTok, YouTube (Shorts), or X/Twitter link and Claude watches it for you — transcribes the audio, reads the on-screen text and visuals, and explains what it's actually about. Runs locally and cross-platform.
★not rated 1 2mo agoA
tokens not measured
originalMIT
An agent driving a browser tends to start a new one rather than use the one already open, and to size its work off the core count. This warns once per session when a tool payload is about to do either. Never blocks.
★not rated 1 1mo agoA
tokens not measured
originalMIT
נגישות אוטומטית לכל דף נחיתה - תקן ישראלי 5568 (WCAG 2.0 AA): הצהרת נגישות מותאמת אישית, כפתור נגישות בכל דף, וצ'קליסט בנייה נגישה שנאכף על כל דף חדש. מבית Brain by Eden Bibas.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Agentic test automation guidelines based on the CIGE standard (Context, Intent, Guardrails, Execution) for authoring self-healing, goal-driven AI test cases.
★not rated 1
changed 11d agoA
tokens not measured
originalApache-2.0
Makes tmux Claude's default for long-running, interactive, and privileged commands. Real blocking waits instead of sleep-polling, true exit codes instead of grepping output, and sudo staged in a pane so you type the password, never Claude.
★not rated 1 29d agoB
tokens not measured
originalMIT
A Claude Code engine that manufactures SaaS landing pages to a spec across four axes (conversion, organic SEO, AI-search/GEO, visual craft). Gated specialist phases (strategy -> copy -> design -> build -> discoverability -> conversion QA -> performance) plus a 10-star scoring loop that refuses to ship below a quality…
★not rated 1 1mo agoA
tokens not measured
originalMIT
A plugin that generates an unattended promotional-video production plan through several structured interviews. A plugin is an add-on that extends what a coding agent can do.
★not rated 1 3mo agoA
tokens not measured
originalMIT
Multi-agent TDD development pipeline: discovery, planning, red tests, implementation, review with complexity ratchet, and a local task registry. Portable across projects via a per-project profile.
★not rated 1 2mo agoA
tokens not measured
originalMIT
Rigorous, verifiable agent workflows for Claude Code. A router over playbooks, an opt-in spec path, durable state on disk, and gates that are code rather than prose.
★not rated 1 29d agoA
tokens not measured
originalMIT
Issue, cancel, and fetch Hungarian invoices via the szamlazz.hu Agent API — directly from Claude Code. VAT-aware, with NAV taxpayer lookup and automatic partner cache. Cross-platform.
★not rated 1 5mo agoA
tokens not measured
originalMIT
A set of rules for how an AI coding agent should work across Claude Code, Codex, Cursor, and Trae. It covers requesting and reporting, follow-up checks, and information sharing.
Guidance for writing C++ back-end services with Drogon, a web framework for building HTTP servers. It focuses on asynchronous code and common problems with callbacks and event loops.
★not rated 1
changed todayA
tokens not measured
originalMIT
A plugin marketplace package built around AI-driven domain-driven design, a way to organise software around the business concepts it models. Its description lists 42 skills, 11 agents, and hooks, including a default secret-protection hook.
The Superpowers software-development methodology executed as a guarded state machine: 21 typed nodes, 96 total exit guards, 9 bounded retry loops, durable run state that survives compaction, and a ledger recording every step that could not run.
★not rated 1 1mo agoA
tokens not measured
originalMIT