Streak-aware break reminders. Hooks log work streaks across every project without the model having to remember anything; when a streak runs long the nudge arrives as an OS notification and asks rather than asserts. Thresholds are time-of-day weighted and retune themselves against a target nudge rate, under floors that.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Design-first Compound Engineering. Adds a design leg to the CE loop: brainstorm -> wireframe -> pick -> hi-fi -> plan, driven by Open Design, with a live browser portal you can chat and mark up in and a clean handoff back to your terminal.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Decompose a large goal into a tree of parallel workers running in isolated git worktrees, collect typed handoffs, replan, repeat until terminal. Idiomatic Claude Code realization of Cursor /orchestrate.
★not rated 1 3mo agoA
tokens not measured
originalMIT
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 yesterdayA
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
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 2d 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 20d 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 2mo 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 1mo 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 19d agoA
tokens not measured
originalMIT