Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
/plugin marketplace add xavierchoi/claude-plugin-codexnpx agentmods add plugins/xavierchoi/claude-plugin-codex/marketplacegit clone --depth 1 https://github.com/xavierchoi/claude-plugin-codexGrade A, and why
claude-plugin-codex scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "claude-plugin-codex",
"interface": {
"displayName": "Claude Code for Codex"
},
"plugins": [
{
"name": "claude-code",
"source": {
"source": "local",
"path": "./plugins/claude-code"
},
"policy": {
"installation": "AVAILABLE",
"authentication": "ON_USE"
},
"category": "Productivity"
}
]
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 21 lines scan A c142acae3dcd
claude-plugin-codex is a plugin published in the GitHub repository xavierchoi/claude-plugin-codex (0 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
wakeflow
A disciplined control loop for multi-window Claude Code work: a controller window dispatches scoped task packages across a tmux-resident fleet, collects immutable target results, obtains independent Test validation, reviews the evidence, and decides the next step. Explicit on-disk state roots keep the run auditable…
llamaparse-mcp
Unlock document processing and Index v2 retrieval workflows with the LlamaParse Platform MCP.
superb
Personal skill collection. Skills are invoked as superb: . craft turns a vague product idea into a decision-rich CRAFT.md brief — it questions, challenges and records, and deliberately stops short of planning. pipeline takes a settled idea to a finished branch, composing the superpowers skills with a zero-assumpt.
ai-safe-driver
Recover from repeated mistakes, failed tool calls, format violations, and conversation drift.
wavedash
Official Wavedash plugins and skills for AI coding agents.
lacuna-music
Generate original AI music from a prompt or your own lyrics — full songs with vocals, instrumentals, and separated stems — through Lacuna's hosted MCP server.