JansenAnalytics/claudex

Autonomous Claude Code agent — Telegram-connected, skill-equipped, self-healing. Reference implementation for building persistent AI agents with Claude Max subscription.

5Stars on the repository
186Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

analyst

01

JansenAnalytics/claudex

Agent Claude Code

Data analyst and market researcher — analyzes data, creates reports, market research. Use for analysis tasks.

not rated 5 3mo ago A 23 tokens original MIT

coder

02

JansenAnalytics/claudex

Agent Claude Code

Code implementation tasks — write features, fix bugs, write tests, refactor. Use for any coding task.

not rated 5 3mo ago A 24 tokens original MIT

documentarian

03

JansenAnalytics/claudex

Agent Claude Code

Write or update inline docs, README sections, and API references after a code change. Use when code has been added/modified and the docs need to catch up, or when a module is undocumented.

not rated 5 3mo ago A 43 tokens original MIT

incident-responder

04

JansenAnalytics/claudex

Agent Claude Code

Diagnose production incidents from logs, metrics, and symptom reports. Trace root cause, propose a fix, and write a short post-mortem. Use when a service is broken, throwing errors, or behaving unexpectedly.

not rated 5 3mo ago A 48 tokens original MIT

researcher

05

JansenAnalytics/claudex

Agent Claude Code

Deep research tasks — web search, multi-source analysis, report writing. Use for any research request that requires thoroughness.

not rated 5 3mo ago A 27 tokens original MIT

reviewer

06

JansenAnalytics/claudex

Agent Claude Code

Code and PR reviewer — analyzes code quality, finds bugs, suggests improvements. Use for code review requests.

not rated 5 3mo ago A 24 tokens original MIT

sysadmin

07

JansenAnalytics/claudex

Agent Claude Code

System administrator — manages services, deploys, troubleshoots infrastructure. Use for ops/infra tasks.

not rated 5 3mo ago B 24 tokens original MIT

tester

08

JansenAnalytics/claudex

Agent Claude Code

Run test suites, parse failures, and propose fixes. Use when the user wants tests run, when CI is failing, or when a code change needs verification beyond static review.

not rated 5 3mo ago A 37 tokens original MIT

writer

09

JansenAnalytics/claudex

Agent Claude Code

Technical writer and content creator — documentation, reports, business plans, pitch decks. Use for writing tasks.

not rated 5 3mo ago A 23 tokens original MIT

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: