tidy-core
15721MCP server Claude CodeCodexCursor +2
MCP server "tidy-core" as configured in rominak/tidy-core. Runs locally from the tidy-core npm package.
Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 282,329 indexed, measured the same four ways as everything else here.
MCP server Claude CodeCodexCursor +2
MCP server "tidy-core" as configured in rominak/tidy-core. Runs locally from the tidy-core npm package.
MCP server Claude CodeCodexCursor +2
MCP server for Disney Lorcana TCG: enrich TCGPlayer collection exports, look up and search cards, auto-build legal decks, audit your collection against live card data, and check the current metagame. Runs locally from the lorcana-mcp Python package.
Skill Claude CodeCodex
Use when reverse-engineering Android APKs on-device in Termux/Shizuku, including unpacking with apktool, inspecting with jadx/smali, patching manifests/resources/code, rebuilding, signing, installing, and iterating with the MCP shell.
Skill Claude CodeCodex
Drive a SPARDA compiled Behavior Runtime to its full potential. Use this whenever you are connected to a backend running the SPARDA Runtime (compiled into a Unified Behavior Graph - UBG) — recognizable by the tools spardagetcontext, spardainfo, spardaconfirm, or composite tools. It teaches the graph-context-first…
Skill Claude CodeCodex
Use when analyzing PRD documents, concept briefs, or feature specs to create implementation plans, breaking work into epics/stories/tasks with dependencies and estimates, or generating PROJECT.md and kanban tracking.
matheuswidder/Acervo-Agents-n-Skills
Skill Claude CodeCodex
Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common API vulnerabilities.
Skill Codex needs its repo
Use when creating or updating a Codex skill package with focused triggers, progressive disclosure, evals, evidence, or tool integration.
Skill Claude CodeCodex
Use when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hallucinations, and cut token usage.
Skill Codex
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when…
Skill Claude CodeCodex
DevOps engineer for CI/CD pipelines, Docker and containerization, deployment automation, infrastructure-as-code, and monitoring. Use this skill whenever the user needs to set up or improve a CI/CD pipeline (GitHub Actions, GitLab CI, CircleCI, etc.), write Dockerfiles or docker-compose configs, deploy to cloud…
MCP server Claude CodeCodexCursor +2
MCP server "code-review-graph" as configured in teakzc/backpack-plus. Launched with C:\Python313\python.exe -m code_review_graph serve.
Skill Codex
A skill for keeping LiveLog's instructions and project documentation aligned with its actual code, tools, services, and operating rules.
j-shelfwood/obsidian-local-rest-api-mcp
MCP server Claude CodeCodexCursor +2
MCP server "obsidian-vault" as configured in j-shelfwood/obsidian-local-rest-api-mcp. Runs build/index.js with node.
Skill Claude CodeCodex
Use Microsoft Teams from a terminal or Node.js with teams-api. Use when an agent needs the CLI to read, search, download, send, edit, or delete Teams content, or needs the SDK for ad hoc analysis, custom automation, or application integration.
Skill Claude CodeCodex
Writing guidance for meeting and daily, weekly, or monthly reports in Korean. It covers preserving facts, recording follow-up actions, tracking deals, and using a consistent report style.
Skill Claude CodeCodex
Drive the CBCTScope CBCT viewer through its MCP server for a human reader. Use when a user asks to open, navigate, window, bookmark, or snapshot a CBCT or dental radiograph in CBCTScope, or to run a reading choreography (MPR survey, pano survey, TMJ setup, replay saved views). Navigation only, never interpretation.
Skill Claude CodeCodex
A research skill that uses Tavily to find public sources, retrieve their readable text, and pass source identifiers to another research worker. Tavily is a web-search service, and this tool is intended for approved research tasks in BriefLoop.
MCP server Claude CodeCodexCursor +2 ✓ vendor
MCP server "advisory" as configured in microsoft/github-advisory-mcp. Runs ${workspaceFolder}/dist/index.js with node. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "gate4agent" as configured in ZENG3LD/gate4agent. Launched with C:/Users/operator/gate4agent/target/release/gate4agent-harness-mcp.exe --session.
Skill Claude CodeCodex
Run the hermeneutic deterministic English drift gate on an assistant draft before sending it when the draft contains numeric claims, completion language, universal quantifiers, or a summary of delegated work.
Skill Claude CodeCodex
Autonomous reverse engineering of compiled apps, binaries, APKs, firmware, and installers on macOS and Windows. Use when the user wants to analyze, decompile, inspect, or understand a binary — including PE/ELF/Mach-O executables, Android APKs, .NET assemblies, Java JARs, firmware blobs, and app bundles. Triggers on…
CitiesSkylinesModding/agents-plugins
Skill Claude CodeCodex
Sweeps the coherent-gameface plugin after the reference target's Cohtml moved. Use when the target's embedded engine updated, when the decompile's cohtml.Net assembly version is newer than the gameface skills' baseline lines, or when mise skills:check-changelog reports a stale ceiling.
Skill Claude CodeCodex
Manage Figma workspaces with the figmanage CLI or MCP. Use for locating and organizing files and projects, access reviews, teams, seats, onboarding, offboarding, cleanup, setup recovery, or handing a managed file to the official Figma MCP for design work.
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package. Needs 1 environment variable to run.
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: