clave

Install

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.

Security

Grade A, and why

clave 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.

.claude-plugin/marketplace.json · 10 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-marketplace.json",
  "name": "clave",
  "description": "Clave agent skills",
  "owner": { "name": "Codika", "email": "[email protected]", "url": "https://github.com/codika-io" },
  "plugins": [
    { "name": "clave", "source": "./plugin", "description": "The Clave agent skills: create-workspace (author a .clave workspace file — groups, sessions, terminals, views, toolbar actions) and recover-sessions (rebuild a lost workspace from the Claude Code transcripts already on disk)", "license": "MIT" }
  ]
}

Changes

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.

Related

Other plugins, from other repositories