Collection of commands that force LLM to reflect on previous response and output. Based on papers like Self-Refine and Reflexion. These techniques improve the output of large language models by introducing feedback and refinement loops.
★not rated 1.8k▲
+24 1mo agoA
tokens not measured
GPL-3.0
Verifies AI agent code before it ships: hardcoded secrets, unbounded loops and retries, hallucinated tool references, oversized prompts, and language-specific quality checks. No telemetry.
★not rated 45
changed 2d agoA
tokens not measured
originalMIT
Camada compilada de contexto para qualquer AI coding tool. Compila projetos em estrutura .first-plan/ com 15 camadas (discovery, conventions, reuse, features, quality, contracts, evolution, runtime) e gera arquivos de instrução tool-specific (AGENTS.md para Codex, .cursorrules para Cursor, .github/copilot-instructions.
★not rated 24
changed 24d agoA
tokens not measured
originalMIT
Orchestrator plugin that weaves planning-with-files, DESIGN.md, memory routing, agent teams, and session handoff into one composable contract for any modern coding agent. Composes existing skills without altering their core. Includes code-to-DESIGN.md harvest and critique.
★not rated 14 5mo agoA
tokens not measured
originalApache-2.0
On Point: the big idea in the first line, the one next action in the second, terse prose after. Substance, exact errors and security are never compressed.
★not rated 7 1mo agoA
tokens not measured
originalMIT
Turns your agent into a smug, arrogant douchebag persona. Sarcastic, condescending, over-confident — zero loss of technical accuracy. Scope-based intensity: normal / full / ultra.
Your AI agent maintains its own context files — a Claude Code plugin with an AGENTS-first model that covers Codex, Copilot, Cursor, Gemini, and 3 more tools. Signal Gate filtering, Context Guard hooks, health scoring, and MEMORY.md promotion.
★not rated 5 3mo agoA
tokens not measured
originalMIT
A Chinese-language enhancement package containing 20 programming skills, including translated and original workflows for tools such as OpenClaw, Claude Code, and Cursor.
★not rated 5 2d agoA
tokens not measured
originalMIT
Design, generate, and run multi-agent AI pipelines — scope-aware, multi-pipeline, spec-driven, write/review-isolated, with step-level create/update/delete and integrated audit.
★not rated 4 3mo agoA
tokens not measured
originalMIT
Converts vague, messy, or under-specified requests into clearer, efficient AI-ready instructions while preserving user intent. Use before solving complex, ambiguous, or high-risk tasks.
★not rated 1 3mo agoA
tokens not measured
originalMIT
Long-term memory for your AI: save decisions and gotchas as you work, then recall them in any session.
★not rated 0 1mo agoA
tokens not measured
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: