Skills, prompts, AGENTS.md files and MCP servers that Codex reads. Skills are shared with Claude Code; the rest is Codex-native. 269,433 indexed, measured the same four ways as everything else here.
A skill that turns rough product ideas, research, interviews, or an existing PRD into a Markdown product requirements document. A PRD explains what to build, how it should be structured, and how to check that it works.
Refine an early idea or creative concept into a coherent, evidence-aware design and durable Markdown master spec/PRD. Use when the user wants to explore, challenge, clarify, or develop an idea before implementation, including related-work research, core-mechanism design, product design, maturity progression, or…
Production-grade engineering gate for writing OR reviewing code. Enforces security, resource safety (memory leaks, unclosed listeners/streams/timers), efficient data access (N+1, pagination/infinite-scroll, over-fetching, backend cost), defensive coding, and evidence-based verification. Use when the user invokes it…
Skill "lark-agent-simple" from Interstellar-code/claud-skills, covering lark agent simple skill, architecture, token efficiency design, component roles and when to use this skill.
Audit Waniwani event tracking across an MCP project. Does an in-depth overview check of the whole app (server, flows, tools, widgets, chat embed), verifies that only events defined in the Waniwani taxonomy are sent, and identifies missing events worth adding at each funnel stage (identify, leadqualified, priceshown…
Isolate read-only CCG search, documentation discovery, and analysis by namespace. Use when working across multiple repositories or services, preventing cross-project graph leakage, federating supported reads, or traversing materialized cross-namespace references. Do not use for graph writes or scoped updates; the user…
Use when the user needs cross-platform desktop GUI control of a native app or window and no MCP server, native CLI, or OS API can safely complete the task.
Multi-agent workflow (tracer/resolver/bypass) for secure code review, exploitability triage, and PoC validation in codebases. Use when conducting structured security research or penetration test analysis.
A product-building guide with two modes: it chooses the right skill before a task and suggests the next step after one is finished. It covers the stages of clarifying an idea, building the product, and getting it running.
A skill for programming PECMD2012 scripts, which are used in lightweight Windows PE startup environments and system tools. It covers GUI tools, initialization scripts, disk partitioning, batch-file conversion, information collection, and debugging.
A follow-on skill for deeper security auditing once a system has been formalized in Lean (e.g. by lean-formal-audit and the audit/ folder exists). It turns the existing Lean formalization into an offensive tool: running Lean code (#eval / decide / #print axioms), using reasoning to form attack hypotheses, doubting and…
MCP image generation server with modular engines and routing. Runs locally from the image-gen-mcp Python package.
★not rated 17 9mo agoA
tokens not measured
originalApache-2.0
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: