Autonomous Claude Code agent — Telegram-connected, skill-equipped, self-healing. Reference implementation for building persistent AI agents with Claude Max subscription.
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code…
Unified dashboard for all cron jobs, systemd services, and Docker containers. Shows schedules, health status, log freshness, errors, upcoming runs, and diagnostics. Use when checking what's scheduled, what's running, what failed, or managing cron jobs.
Use when: the user provides a CSV, JSON, or NDJSON file and wants analysis, filtering, aggregation, or exploration. Also use when you have structured data from an API and want to query it.
Autonomous data quality validation — schema inference and validation, completeness/uniqueness/consistency checks, statistical anomaly detection, time-series gap detection, referential integrity, dataset comparison and drift detection. Supports CSV, JSON, SQLite, APIs. Use after any data pipeline work.
Autonomous UI/UX review — screenshots every page at mobile/tablet/desktop (full-page scrolling), analyzes with vision models for layout bugs, checks accessibility (axe-core), audits contrast/colors/fonts/spacing for design system inconsistencies, detects dead buttons/links, overlapping elements hiding text/buttons…
PDF/DOCX/XLSX/image document intelligence — text extraction, table parsing, OCR, financial statement analysis, contract clause detection, document classification, and format conversion. Use when reading, analyzing, extracting data from, or converting documents.
Ensures documentation is accurate, complete, and actually works — catches documentation rot before users hit it. Validates code examples, checks links, compares API/CLI docs against reality, detects stale docs, and scores completeness.
Queue an external action (Telegram message, shell command, GitHub comment, PR merge, file write) for the user's explicit approval before it runs. Use when you want to take an outward-facing or irreversible action that needs sign-off first.
Generate end-to-end tests for web applications using Playwright. Create test files from user flow descriptions, page snapshots, or existing page analysis.
Collects and queries macroeconomic data — yield curves, central bank policy rates, forex rate differentials, FRED US economic indicators (CPI, GDP, NFP, unemployment), and the economic calendar. Use when fetching, storing, or querying interest rates, bond yields, rate diffs, or economic releases for trading and forex…
Monitor application logs and stderr in real-time for errors, crashes, and exceptions. Auto-capture stack traces, alert on new error patterns, track error rates.
An append-only structured JSONL event log giving Kite continuity across sessions — without reading every log file.
★not rated 5 2mo agoA23 tokens
originalMIT
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: