Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 281,303 indexed, measured the same four ways as everything else here.
Use linctl as the Linear control surface for agent-safe issue, project, Cycle, ProjectMilestone, organization, user, team, search, release, initiative, customer, notification, attachment, comment, and metadata work. Prefer it over Linear MCP, raw GraphQL, or ad hoc API calls when linctl covers the operation; use…
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, 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.
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
Persistent agent memory (episodic log + versioned continuity + an immune system that gates graduation) plus a prospective spore layer and an on-demand crystallized-pattern tier, via anneal-memory. Use in any project wired for anneal-memory — an ANNEALMEMORYDB env var, an anneal://continuity MCP resource, or memory…
The Universal Agent Gateway (UAG) enables in-process agentic automation using Form.io. Runs locally from the @formio/uag npm package. Needs 15 environment variables to run.
★not rated 12 2d agoA
tokens not measured
originalMIT
The Active Circuit Breaker & Cost Tracker for AI SaaS. Enforce hard API budgets, track GPT-4o/Claude costs, and stop runaway agents before they break your unit economics.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Build or maintain project multi-agent collaboration, including team setup, roles, session routing, handoff and protocol repair. Existing departments handle routine development and review through project role and TASK files.
★not rated 12▲
+1
changed 2mo agoA40 tokens
original
Build conversational AI chatbots with native Hebrew support, including WhatsApp Business API integration, Telegram bot scaffolding, web chat widgets, Hebrew NLP patterns, and RTL chat UI components. Prevents common Hebrew chatbot mistakes like broken RTL alignment, incorrect gender inflections, and poor tokenization…
Allow AI systems to read, send, archive, and manage emails via Gmail. Runs locally from the gmail-mcp npm package. Needs 1 environment variable to run.
Launch-gate security review for the Vibe CRM Security Lab (NorthStar CRM) — a Next.js 16 App Router + Supabase + OpenAI app. Audits the codebase against the OWASP Top 10 2025, reports each issue in plain language with the exact file, severity, and the concrete fix (using the repo's own /api/fixed/ routes and…
MCP server "claude-code-explorer" as configured in ShothikTest/claude-code-src. Runs mcp-server/dist/index.js with node. Needs 1 environment variable to run.
ROS2 graph: topics, nodes, services, TF, actions (mock + live). CLI ros2-mcp + MCP stdio serve. Use when the user mentions ros2-mcp, /ros2-mcp, or related domain work. One-command Grok install from GitHub.
MCP server for interactive terminal sessions (SSH, REPLs, database CLIs). Runs locally from the terminal-mcp Python package. Needs 2 environment variables to run.
★not rated 12▲
+1 3mo agoA
tokens not measured
originalMIT
Async email-style messaging with the human user via a GitHub issue used as a mailbox. Reach for the nobox tools whenever the user wants to be reached asynchronously (they're stepping away, the task will take a while, they ask to "leave a note", "ping me later", "check messages", or "email me when you're done").…
Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM. Runs locally from the toon-memory npm package. Needs 6 environment variables to run.
★not rated 12 3mo agoA
tokens not measured
originalMIT
Apply Michael's academic writing style when drafting or editing text. Use when writing LaTeX prose, paper sections, abstracts, or any academic text for Michael.
Enrich an existing PKUP report directory — group commits into tasks, filter out non-creative groups, and write Polish descriptions. Use when the user has already generated a PKUP report and wants to clean it up or add "Zaprojektowałem..." descriptions.
AI Skill for CH57x BLE microcontroller firmware development. Used when users need to create, modify, or debug CH57x embedded projects, including BLE peripheral/central/mesh applications, peripheral driver configuration, IAP/OTA updates, and power management. Supports CH573, CH571 and other chips in the CH57x family.…
End-to-end FeatBit experimentation workflow with Bayesian A/B/n analysis. Use when shaping product intent, writing a hypothesis, defining feature flags and rollout strategy, designing metrics and instrumentation, creating or analyzing experiment runs, deciding continue/pause/rollback/inconclusive, or capturing…
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: