jq plugins

Scaffold production-grade Claude Code plugins with marketplace integration, validate structure and schemas, audit for security vulnerabilities and best practices, and automate semantic version bumps across manifests and catalogs using auto-invoked skills and interactive commands.

Fully manage Ubiquiti UniFi networks via Rust CLI, TUI, and AI agent for VLANs, SSIDs, firewalls, NAT, DHCP reservations, clients, devices, events, stats, DPI, backups, and raw API access. Audit configurations for security vulnerabilities like open WiFi or permissive rules with ranked remediations. Run health checks on controllers, devices, alarms, and clients. Deploy autonomous agents for diagnostics and ongoing control.

Build, deploy, and operate AI agents on AWS with Amazon Bedrock AgentCore — scaffold projects, connect tools via Gateway, debug failures, deploy with rollbacks, enforce security, and evaluate agent quality.

Estimate per-turn token costs for .claude/ configurations and CLAUDE.md files, classifying components as always-loaded, path-scoped, or invoked-only, ranking top contributors, flagging overruns, and fetching exact counts via Anthropic API to optimize Claude context budgets.

Run a multi-lens code review pipeline: deep analysis, automated fix loops, manual promotion of findings, and injection of external issues, all synthesized into a single artifact for PR review.

Delegate tasks to a cloud Devin session with its own VM, shell, browser, and full repo access, enabling parallel work, long-running processes, browser automation, and large refactors.

Orchestrate multi-model code reviews by running Claude, OpenAI Codex, and Gemini in parallel, then synthesizing their opinions into a consensus verdict with automated setup and cleanup.

Query scientific databases like PubMed, arXiv, bioRxiv, medRxiv, ChEMBL, DrugBank, ClinicalTrials.gov, FDA labels, Open Targets, and patents using natural language via Valyu semantic search. Retrieve full-text content, images, compounds, trials, drug data, and relevance scores to accelerate biomedical research, drug discovery, and AI analysis workflows.

Displays real-time context, rate limit status, tool activity, and token costs in the Claude Code status bar, using pure bash and jq.

Generate AI images and videos from text prompts via Leonardo.Ai CLI in your terminal. Specify models, dimensions, enhancements; poll job status, download results to files/directories; list models and check credits.

Daily driver skill pack for Claude Code: read public URLs into clean Markdown, draw hand-drawn diagrams with Excalidraw, build interactive 3D scenes and landing pages, organize GitHub stars by category, count lines across multi-language repos, generate slide decks, configure custom personas, and fetch release notes updates.

Manage Buildkite CI/CD pipelines end-to-end: create, debug, and convert pipeline configurations; run builds locally; orchestrate job steps with agent commands; and automate via API and CLI.

Run long-running, unattended batch agents in Claude Code by defining tasks in a CSV table and orchestrating them through a shift-based workflow with self-validation, retries, and subprocess dispatching.

Use the bitdrift Capture mobile observability platform: install and instrument the SDK on iOS, Android, and React Native; run the CLI to debug app health via sessions, issues, and live account data; and search product documentation for setup and API details.

Drive Navaris CLI with AI to fully manage isolated dev sandboxes: create/start/stop/destroy using Incus or Firecracker backends, exec one-shot commands with env/timeout, attach persistent tmux terminals, create/restore snapshots, promote/register images, and handle async operations.

Enforces a TDD-first team workflow: every change starts as a plan with tests, then iteratively passes those tests before archiving to a regression suite. Reports progress to Slack/Discord and skips obsolete tests via supersede chains.

Generate EN 16931-compliant e-invoices (XRechnung, ZUGFeRD) or plain PDFs by calling the public Scribo HTTP API with curl and jq, no signup or MCP server required.

Replace vague planning with structured PRDs, technical designs, and ordered tasks that keep Claude grounded during large feature implementation. Generates TASKS.json/md files with phased tasks, dependencies, and acceptance criteria, then automates end-to-end implementation and review against those artifacts.

Operate Crypto.com Exchange via agent-first CLI: fetch real-time market data, execute live trades with dry-runs/safety tiers, manage margins/staking/funding/wallets, analyze portfolios, generate reports, and enable MCP agent autonomy from observation to full trading.

Safely run autonomous Claude Code in production by deploying hooks that block risky Bash commands on unprotected branches, check syntax after edits, monitor context usage, log sessions, and verify setup with diagnostics and guided configuration.

Run parallel AI reviews from multiple models (Codex, Gemini, Kimi, Qwen, etc.) to analyze plans, debate contradictions, and synthesize a consensus verdict—with personality-driven reviewers like Skeptic and Architect.

Manage Arize ML observability projects and datasets via ax CLI skills to create from CSV/JSON/Parquet files, list with pagination, retrieve details, delete, export data, and extract IDs using jq for automated platform operations and analytics workflows.

Monitor Claude Code's context usage, 5-hour rate limits, and 7-day usage via color-coded progress bars, plus current folder and git branch, in a cross-platform status line.

Navigate and analyze codebases semantically with tree-sitter: search symbols by regex, trace call sites and usages, explore class APIs and structures, grep files and contents, scan git commit history, query configs via jq or XPath, and switch workspaces—all locally without LSP setup.

Add a beautiful statusline to Claude Code showing git status, model name, context details, and rate limits, with easy install, removal, and updates.

Label a GitHub issue to trigger Zapat's autonomous pipeline powered by Claude Code, which builds, tests, and delivers a merge-ready PR. Setup interactive agent teams, monitor pipeline health with auto-fixes, and add repos for ongoing automation.

Run AI-human collaborative issue tracking in a terminal Kanban TUI (viban). Register problems as prioritized issues, assign to AI agents for automated analysis/implementation/testing in isolated git worktrees, auto-create GitHub PRs, review changes in IDE, approve to merge/cleanup or reject with feedback to iterate.

Enforce a minimum percentage of human-written code by mentoring developers, blocking AI attribution, coaching from session transcripts, and preventing silent data-loss from Timeback/QTI APIs.

Fully automate Wix eCommerce management in Claude Desktop: AI-generate products from images with descriptions/pricing/categories, auto-categorize via analysis, CRUD inventory/orders/customers/events/CMS data, configure taxes/shipping/coupons, segment for targeted emails, build Kanban pipelines tracking carts-to-sales, audit store health, generate revenue analytics and dashboards.

Manage shared, tiered coding memory (canonical/team/user) for architecture decisions, PR notes, and codebase handoffs using Redis/SQL backends. Auto-capture/load memory in Claude sessions via hooks, inspect and sync via CLI/TUI, promote notes, and integrate with git repos for persistent team knowledge.

Store, semantically search, and graph-link persistent project knowledge like decisions, gotchas, patterns, and learnings across Claude sessions. Capture memories from conversations or git changes, check recent work against stored warnings, create multi-agent thinking docs, and monitor memory health with agents and CLI commands.

Enforce automated code review gates--autofix, architecture verification, and conversation review--blocking Claude Code sessions until all checks pass, with toggleable gates and unattended fix branches.

Convert static web or Next.js projects into ArcBlock blocklets with a provided DID, automate git branch detection and PR creation following repo conventions, set up blocklet dev environments by cloning repos and installing deps, guide onboarding for new developers, and streamline releases via version bumps and changelog updates.

Capture, retrieve, and synchronize structured project knowledge—architecture decisions, lessons learned, and session summaries—into a local knowledge graph with git metadata, FTS5 search, and GitHub issue/PR linking.

Trace Konflux container builds from image references back to build logs, source commits, and pipeline URLs using cosign provenance attestations

Manage an Obsidian vault using the PARA methodology: capture web pages, voice memos, and URLs to an inbox, then classify, enrich, and route items into projects, areas, and resources with validated frontmatter and git auto-commit.