Deep white-box OSWE-style web app security audit via /oswe:audit (PHP, Node.js, Python, Java, .NET), guided by a deterministic application graph (vendored tree-sitter) — Markdown + visual HTML reports. By Laucked Security.
★not rated 1
changed 7d agoA
tokens not measured
originalMIT
A Claude Code plugin that creates a learning brief immediately after the agent changes code. The brief shows what changed, explains Python syntax, and traces logic and data flow.
★not rated 1 3mo agoA
tokens not measured
originalMIT
Automatic tool-call review for Claude Code. A local encoder scores every proposed tool call before it runs, approving safe work and blocking dangerous calls with an explanation the agent can act on.
★not rated 1 3mo agoA
tokens not measured
originalApache-2.0
Turns standing preferences into well-formed, correctly-scoped CLAUDE.md rules. Asks one question at a time, picks global vs project scope, and keeps rules files small enough that Claude actually follows them. Runs no background code.
★not rated 1 14d agoA
tokens not measured
originalMIT
Branded presentation deck toolkit. Ships three skills: deck-brand-init (brand.yaml scaffolding), deck-create (conversational HTML deck authoring), and deck-publish (HTML to PDF or PPTX via Puppeteer + pptxgenjs, both pixel-perfect screenshot and fully-editable modes). Works in Claude Code and GitHub Copilot CLI.
Autonomous coding agent that turns Notion and Jira PRDs into shipped pull requests. Reads requirements, analyzes the codebase, generates a task plan, implements each task with tests, commits, and opens a PR. Includes a 24/7 GitHub Actions queue processor, two-way Slack Q&A, and a built-in status command for weekly sp.
★not rated 1 6mo agoA
tokens not measured
originalMIT
A graph of atomic claims that LLMs walk natively as semantic engines. Eight core verbs (extract, connect, walk, audit, learn, init, anneal, dream) plus an opt-in surrender system (no-surrender, teach). No queues, no phase machines, no invisible hooks.
★not rated 1 6mo agoA
tokens not measured
originalMIT
Auto-detects API keys and secrets in your prompts, saves them to chmod-600 files in /.claude/secrets/, blocks the original prompt, and re-submits a sanitized version via OS-level paste automation. Cross-platform (macOS, Linux, Windows). Zero-friction secret hygiene for Claude Code.
★not rated 1
changed 1mo agoA
tokens not measured
originalMIT
מגדיל ראש — do more than the literal ask. Ships the complete feature, not the happy path: edge-case checklists per domain, asks the right scoping questions first, reports terse.
★not rated 1 5mo agoA
tokens not measured
originalMIT
Route tasks between Claude Code and Codex CLI — Subscription Efficiency Maximizer. Automatically routes tasks to the optimal CLI based on task type and budget.
★not rated 1 8mo agoA
tokens not measured
originalMIT
Keyword -> browser moodboard -> brand guidelines + UI code. Fetches design references from Dribbble, Pinterest, Behance and the open web, lets you pick favorites in a visual moodboard, then recreates the look as a brand spec and starter components.
Build a customer support AI Agent from your website, try it with a real customer question, and put it live on your site, WhatsApp, Discord, Telegram, Instagram, Slack or email. Review its conversations, CSAT and handoffs, triage what needs a human, and improve its knowledge, settings and AI Actions without leaving…
★not rated 1
changed 5d agoA
tokens not measured
originalMIT