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 copyleftdev/kaheanpx agentmods add plugins/copyleftdev/kahea/marketplacegit clone --depth 1 https://github.com/copyleftdev/kaheaGrade A, and why
kahea 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
{
"$schema": "https://json.schemastore.org/claude-code-marketplace.json",
"name": "kahea",
"owner": {
"name": "copyleftdev",
"url": "https://github.com/copyleftdev"
},
"description": "Agent-first HTTP and finite WebSocket testing with deterministic invocation.",
"plugins": [
{
"name": "kahea",
"source": "./plugins/kahea",
"description": "Seal, test, and invoke HTTP and finite WebSocket APIs with exact capability grants.",
"version": "0.3.1",
"author": {
"name": "copyleftdev",
"url": "https://github.com/copyleftdev"
},
"category": "development",
"tags": [
"openapi",
"asyncapi",
"websocket",
"api-testing",
"mcp",
"ai-agents"
]
}
]
}
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 · 31 lines scan A 0f72583434ad
kahea is a plugin published in the GitHub repository copyleftdev/kahea (2 stars, last pushed 4d ago), licensed Apache-2.0. 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
pentest
Full penetration testing framework - 69 attack categories across 16 domains covering OWASP, injection, authentication, cloud, and more.
patchman
Defensive security audit mode for authorized code review and architecture assessment.
patchman-marketplace
Plugin marketplace listing 1 plugin: patchman.
dq-awesomeqa
Full QA lifecycle plugin — guided STLC journey for UI, API, Accessibility, and Performance testing.
dq-awesomeqa
Full QA lifecycle plugin for UI, API, Accessibility, and Performance testing — guided by a senior QA consultant.
supabase-pentest-skills
Plugin marketplace listing 10 plugins: supabase-orchestration, supabase-detection, supabase-extraction, supabase-audit-api, supabase-audit-storage.