Agent Codex
Stack audit. Finds overlaps, waste, security risks. Read-only.
1 21d ago A 20 tokens
original MIT
1Stars on the repository
25Mods indexed here, across every type
21d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Agent Codex
Cleanup. Removes temp, debug, unused code. Confirm before delete. May edit after confirmation.
1 21d ago A 24 tokens
original MIT
Agent Codex
Systematic debugger. One hypothesis at a time. Evidence required. May apply minimal fixes.
1 21d ago A 23 tokens
original MIT
Agent Codex
Reuse decision engine. Finds existing code before writing new — classifies REUSE/EXTEND/COMPOSE/REFERENCE/NEW. Never duplicate. Read-only.
1 21d ago A 37 tokens
original MIT
Agent Codex
Engineering planning. Intent Discovery → context → constraints → reuse → alternatives → roadmap. Read-only — never implements, never edits source code.
1 21d ago A 32 tokens
original MIT
Agent Codex
Review gate with risk-based routing. L0=output check, L1=lint, L2=full review, L3=expert+threat model. Blocks merge if critical issues found. Read-only.
1 21d ago A 48 tokens
original MIT