8,228 mods tagged anthropic that install into Codex, measured the same four ways as everything else here: what each costs in tokens on every session, what a security scan found and why, whether it is the original, and what changed.
MCP server Claude CodeCodexCursor +2
MCP server for self-hosted GitLab — pipelines, schedules, branches, merge requests and repository files. Runs locally from the gitlab-ci-mcp Python package. Needs 4 environment variables to run.
Skill Claude CodeCodex
Produce a clean handoff to a fresh Claude Code window. Use when the current conversation is too long (>400K tokens, hallucinations, lost context, or the user wants to close the window). "/next" produces a handoff, "/next list" shows all pending, "/next remove X" deletes one.
MCP server Claude CodeCodexCursor +2
Inspect and score any MCP server 0-100 on publishability, schema and protocol before publish. Runs locally from the @incultnitollc/mcp-probe npm package.
Gremoryzlk/claude-warhammer-40k-skill
Skill Claude CodeCodex
Applies grimdark Warhammer 40K Imperium narration to EVERY response while this skill is enabled — all topics, all message lengths, not just 40k-related questions. Always consult and apply once active, until user disables it or asks for a plain answer.
Skill Claude CodeCodex
Prevents prompt-cache thrash and runaway token burn in long or image-heavy agent sessions. Load BEFORE reading images/screenshots (visual QA, render checks, UI verification, diagram review) in a conversation that already has substantial history, when running long agentic loops with periodic wake-ups, or when the user…
Rijul1204/rashedul-agentic-engineering
Skill Claude CodeCodex
Multi-role review of a plan, design doc, PR, or code change from four independent hats — Senior Software Engineer, Engineer, AI Education Engineer, and Product Owner — each producing a 0–100% confidence score with mandatory written justification AND ranked P0–P3 findings, then a fifth deduplicator agent that merges…
Skill Claude CodeCodex
Priority-ordered rulebook of core UX/UI laws, cognitive-psychology principles, Nielsen's usability heuristics, and accessibility requirements that Claude must actively apply (not just cite) whenever it designs, builds, redesigns, reviews, or critiques any user interface — websites, web/mobile apps, dashboards, forms…
Skill Claude CodeCodex
The door check for prototype and AI-built apps - decides whether an app gets to meet real users, and says exactly why not. Use this whenever someone asks if their app is ready to launch, deploy, or go live; wants a pre-launch, security, or "what am I missing" review; mentions moving from prototype to production; or…
chayan-1906/Claude-Lens-Next.js
MCP server Claude CodeCodexCursor +2
Next.js development tools MCP server with stdio transport. Runs locally from the next-devtools-mcp npm package.
MCP server Claude CodeCodexCursor +2
Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the chrome-devtools-mcp npm package.
A-cat-with-carrots/pm-daily-brief-skill
Skill Claude CodeCodex
A Chinese-language daily intelligence report for an AI product manager. It gathers Product Hunt launches, GitHub Trending projects, and popular Hacker News items, then produces Markdown and PDF reports.
joshuafuller/atak-plugin-skill
Skill Claude CodeCodex
Use when building, debugging, testing, or shipping an ATAK (Android Team Awareness Kit) plugin - scaffolding from the SDK template, getting it to actually load on a device, running instrumented tests inside ATAK, and preparing a submission to TAK's third-party signing pipeline. Triggers on ATAK plugin work, "plugin…
Skill Claude CodeCodex
Graph-based reasoning pipeline — contracts, stages, modes in separate files with a forward DAG-shaped pipeline + bounded conditional control-flow. Progressive disclosure: SKILL.md is a router; full instructions load per stage from contracts/, stages/, modes/, quality/ + reference docs. Zero Python dependency. 8…
Skill Claude CodeCodex
Diagnose a failing AI agent run with Pisama. Turns a trace into a root-cause report: what failed, which agent failed at which step, every detection with a calibrated confidence, and an apply-ready fix. With a connected key it returns a ready-to-paste CLAUDE.md/.cursorrules guardrail plus the commands to verify it, and…
Skill Claude CodeCodex
A Russian-language framework for solving business and organizational problems through an eight-step consulting process. It treats the user as the decision-making partner and produces items such as a problem statement, issue tree, analysis, recommendations, and communication plan.
Skill Claude CodeCodex
Use this skill when the user is building against Anthropic APIs or SDKs, including @anthropic-ai/sdk, anthropic, or Agent SDK integrations.
novalidesignl-ship-it/fable-like-skill
Skill Claude CodeCodex
Fable-5-style engineering discipline for coding and multi-step work — act decisively when you have enough info, ground every progress claim in tool output, avoid over-engineering and unrequested cleanup, verify with fresh context, lead with the outcome. Plus general agent hygiene (know your tools first, gather context…
Skill Claude CodeCodex
Write and execute IBM SPSS Statistics syntax following SPSS conventions and run SPSS MCP analyses defensively. Use when the user asks to run statistical analysis (frequencies, descriptives, regression, t-test, ANOVA, correlations, factor analysis, crosstabs, MDS/PROXSCAL, clustering, survival, mixed models, etc.)…
vbalasu/grill-me-store-decisions
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree, AND persist the full decision tree (selected + rejected options, recommendations, AND cost tradeoffs) to decision-tree.md in the current repo so choices can be revisited later. Use…
JosephOIbrahim/UnrealEngine_Bridge
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP server "unreal" as configured in JosephOIbrahim/UnrealEngineBridge. Runs ue_mcp.mcp_server with python.
Skill Claude CodeCodex
Transforma um BRIEF (ou ideia já discutida) em PLAN.md atômico — tasks com critério verificável, vertical slices, must-haves observáveis, esforço estimado e pontos de reset de contexto. Sem código no plano. Auto-suficiente para reset — uma nova sessão consegue retomar lendo só o PLAN.md. Use quando o usuário disser…
Skill Claude CodeCodex
Analyze conversation and update CLAUDE.md, rule files, and/or any skills, commands, or agents that were used — based on user feedback vs agent behavior. Use this skill at the end of any conversation where corrections, misunderstandings, or new patterns emerged, especially when a skill, command, or agent underperformed…
Skill Claude CodeCodex
Design production-grade agentic AI systems from a natural-language use case. Runs a clarification loop, walks grounded decision trees (workflow vs agent, RAG vs fine-tuning, single vs multi-agent, autonomy tiers), and emits a detailed enterprise system design document with embedded interactive architecture, sequence…
Skill Claude CodeCodex
Full-depth audit (a11y, UX, perf, SEO, security, DB, architecture, legal compliance, ops, observability) of a project. Audits by reading the source directly — installs nothing, writes nothing outside docs/audits/. Reports findings with file:line evidence and calibrated severity, optionally mitigates as discovered. Use…
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: