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 openwong2kim/wmuxnpx agentmods add plugins/openwong2kim/wmux/claudegit clone --depth 1 https://github.com/openwong2kim/wmuxGrade A, and why
claude 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 2d ago.
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": "wmux-claude-integration",
"version": "0.3.0",
"description": "Deterministic Claude Code → wmux notifications via Stop / SubagentStop / SessionStart / PreToolUse hooks. Replaces wmux's regex-based agent detector with 100%-accurate hook signals when this plugin is installed.",
"author": {
"name": "wmux",
"url": "https://github.com/openwong2kim/wmux"
},
"homepage": "https://github.com/openwong2kim/wmux",
"license": "MIT",
"keywords": ["wmux", "terminal", "notifications", "hooks"]
}
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.
- 2d ago First seen · 13 lines scan A 6f70c39a728c
claude is a plugin published in the GitHub repository openwong2kim/wmux (362 stars, last pushed 2d 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 2026-08-30.
Other plugins, from other repositories
cli
Run HeadlessX website, search, YouTube, and jobs workflows from the terminal.
draft-plugins
Plugin marketplace listing 1 plugin: draft.
coaltipple
CoalTipple — model/effort router for Claude Code. Delegates a task you CAN do but is large+cheap DOWN to a lower tier to save tokens; escalates a task beyond the current tier UP for quality — up to Fable 5, the top rung (a consent-gated, real-money spawn). Two-knob routing (tier × effort, effort-before-tier), an alias.
hunch
A git-native reasoning graph of decisions, bugs, and invariants for your codebase — queried and enforced at reasoning time. Adds the hunch MCP tools plus /hunch:capture, /hunch:heal, /hunch:why, /hunch:fix, /hunch:fragile.
sipcode
Token-economy observatory for Claude Code: forensic per-session audit, A/B savings verifier, reproducible benchmark, and cost prediction — directly in Claude chat. Auto-installs via npx on first use; no separate npm install required.
ai-psychiatry
Semantic executive control for loopholes, underthinking, overthinking, evidence, recursion, context, memory, relentless execution, and reliable delivery.