81,390 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Visual terminal state indicators for Claude Code sessions using OSC escape sequences. Changes background color and tab title based on Claude's state (processing, permission, idle, complete, compacting, subagent, toolerror).
★not rated 3 26d agoA
tokens not measured
originalMIT
Use when working in the harness-config repository and Codex needs to validate, preview, activate, or explain Harness config dogfooding with the local @harnessconfig/cli package.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
When the agent is about to output long markdown (weekly reports, PR reviews, design comparisons, concept explainers, flowcharts, design systems and other deliverables meant for human reading), proactively evaluate whether to render it as HTML instead. Based on the 20 examples from ThariqS/html-effectiveness. Only…
A general operating guide for software-engineering work by coding agents. It covers keeping the goal fixed, finding causes before patching, verifying results, and working concisely.
Orchestrates Gemini CLI and Copilot CLI agents for comprehensive research, development, and analysis tasks. Coordinates multiple AI perspectives, consolidates findings, and provides consensus-based recommendations. Use PROACTIVELY for complex tasks requiring multi-agent collaboration.
Portable user-context for AI tools. Read identity, voice, and preferences from /.me/ at session start. The /me slash command manages content. Reference implementation of the dot-me v0.3 spec.
★not rated 3 3mo agoA
tokens not measured
originalMIT
Propose a reviewable multi-agent workflow as a blueprint — pick and name the pattern (map-reduce, pipeline, tournament, loop-until-dry, dag), emit its shape as an agentstack-blueprint JSON block, and WAIT for the user to approve / reject / edit before authoring and running it via agentstack more workflow run.
MCP server "geond" as configured in geondongkim/geond-agent-protocol. Launched with uv --directory C:/path/to/geond-agent-protocol run geond-mcp. Needs 5 environment variables to run.
★not rated 3 2mo agoA
tokens not measured
originalApache-2.0
A recipe for building a model of a user's preferences from an AI agent's conversation logs. It organizes decisions and outcomes into files that can inform memory, rules, or system prompts.
A Chinese-language companion skill that responds in the style of an MBTI personality type. MBTI is a system that groups personality preferences into sixteen types.
A set of operating instructions for safely changing and synchronising CC Switch, an app that manages prompts, skills, MCP servers, providers, and Codex model settings across several AI coding applications.
Expert knowledge for building Quarkus applications with Bazel using the rulesquarkus build system. Use when user asks about Quarkus+Bazel builds, augmentation, or troubleshooting.
Utiliza este skill cuando el usuario pida dibujar pizarras, diagramas de arquitectura, bocetos UI o esquemas de cajas libres que requieran geometría manual 2D y un alto grado de personalización posterior. Genera el código fuente JSON de Excalidraw (.excalidraw) para importación directa.
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: