Cursor rule Cursor
Agentic workflow patterns—when to use agents vs workflows, prompt chaining, routing, evaluator-optimizer.
not rated 2 7mo ago A 424 tokens
original MIT
Cursor rule Cursor
Coding agents—prompt pattern for code tasks, error-proofing file/edit tools, minimal scaffolding.
not rated 2 7mo ago A 348 tokens
original MIT
Cursor rule Cursor
Context engineering for agents—finite context, prompt altitude, compaction, note-taking, sub-agents.
not rated 2 7mo ago A 377 tokens
original MIT
Cursor rule Cursor
Design patterns (GoF) and file size conventions for sweagent TypeScript codebase.
not rated 2 7mo ago A 894 tokens
original MIT
Cursor rule Cursor
Best practices for long-running agents (initializer/coding pattern, incremental progress, clean state).
not rated 2 7mo ago A 421 tokens
original MIT
Cursor rule Cursor
Multi-agent systems—orchestrator-worker, delegation, scaling, evaluation, production.
not rated 2 7mo ago A 834 tokens
original MIT
think-tool
07Cursor rule Cursor
When and how to use a "think" tool or extended thinking for complex tool-use agents.
not rated 2 7mo ago A 403 tokens
original MIT
tool-design
08Cursor rule Cursor
Tool design for agents—self-contained tools, minimal sets, token-efficient results, progressive disclosure.
not rated 2 7mo ago A 676 tokens
original MIT
Cursor rule Cursor
Evaluation-driven tool improvement—prototype, evaluate, analyze, collaborate with agents.
not rated 2 7mo ago A 395 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: