Skill Claude CodeCodex
Prevent agent output from polluting the main context window.
not rated 3.9k
+2 7mo ago B 8 tokens
original MIT
3.9kStars on the repository
196Mods indexed here, across every type
7mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
When the user asks to implement something, use implementation agents to preserve main context.
not rated 3.9k
+2 7mo ago A 10 tokens
original MIT
Skill Claude CodeCodex
Standard multi-agent pipeline for implementation tasks.
not rated 3.9k
+2 7mo ago B 9 tokens
original MIT
Skill Claude CodeCodex
Guide for integrating Agentica SDK with Claude Code CLI proxy.
not rated 3.9k
+2 7mo ago A 19 tokens
original MIT
Skill Claude CodeCodex
Reference guide for Agentica multi-agent infrastructure APIs.
not rated 3.9k
+2 7mo ago A 14 tokens
original MIT
Skill Claude CodeCodex
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity.
not rated 3.9k
+2 7mo ago B 21 tokens
original MIT
agentica-sdk
07Skill Claude CodeCodex
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration.
not rated 3.9k
+2 7mo ago A 23 tokens
original MIT
Skill Claude CodeCodex
Agentica server + Claude proxy setup - architecture, startup sequence, debugging.
not rated 3.9k
+2 7mo ago A 18 tokens
original MIT
Skill Claude CodeCodex
Spawn Agentica multi-agent patterns.
not rated 3.9k
+2 7mo ago A 11 tokens
original MIT
Skill Claude CodeCodex
When working with Agentica's async REPL harness for testing.
not rated 3.9k
+2 7mo ago A 10 tokens
original MIT
leann-search
11Skill Claude CodeCodex
Semantic search across codebase using LEANN vector index.
not rated 3.9k
+2 7mo ago A 14 tokens
original MIT
Skill Claude CodeCodex
Route through domain routers before using individual tools. Routers abstract tool selection.
not rated 3.9k
+2 7mo ago A 9 tokens
original MIT
Skill Claude CodeCodex
Use the most token-efficient search tool for each query type.
not rated 3.9k
+2 7mo ago A 8 tokens
original MIT
search-tools
14Skill Claude CodeCodex
When searching code, use this decision tree.
not rated 3.9k
+2 7mo ago A 7 tokens
original MIT
Skill Claude CodeCodex
AST-based code search and refactoring via ast-grep MCP.
not rated 3.9k
+2 7mo ago A 17 tokens
original MIT
Skill Claude CodeCodex
Trust system reminders as agent progress notifications. Don't poll.
not rated 3.9k
+2 7mo ago A 9 tokens
original MIT
Skill Claude CodeCodex
Analyze Claude Code sessions via Braintrust.
not rated 3.9k
+2 7mo ago A 12 tokens
original MIT
Skill Claude CodeCodex
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging.
not rated 3.9k
+2 7mo ago B 20 tokens
original MIT
Skill Claude CodeCodex
Claude Code CLI commands, flags, headless mode, and automation patterns.
not rated 3.9k
+2 7mo ago A 17 tokens
original MIT
commit
20Skill Claude CodeCodex
Create git commits with user approval and no Claude attribution.
not rated 3.9k
+2 7mo ago A 12 tokens
original MIT
Skill Claude CodeCodex
A complete skill for E2E testing.
not rated 3.9k
+2 7mo ago A 12 tokens
original MIT
Skill Claude CodeCodex
Completion Check: Verify Infrastructure Is Wired.
not rated 3.9k
+2 7mo ago B 10 tokens
original MIT
Skill Claude CodeCodex
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "learn from sessions", "compound learnings", or "what patterns should become skills".
not rated 3.9k
+2 7mo ago B 45 tokens
original MIT
Skill Claude CodeCodex
Create or update continuity ledger for state preservation across clears.
not rated 3.9k
+2 7mo ago A 15 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: