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 bang9/ai-toolsnpx agentmods add plugins/bang9/ai-tools/claude-ircgit clone --depth 1 https://github.com/bang9/ai-toolsGrade A, and why
claude-irc 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": "claude-irc",
"version": "v2.17.1",
"description": "IRC-inspired inter-session communication for Claude Code agents",
"author": {
"name": "Airen Kang",
"url": "https://github.com/bang9"
},
"repository": "https://github.com/bang9/ai-tools",
"license": "MIT",
"keywords": [
"irc",
"communication",
"agent",
"inter-session",
"collaboration"
],
"hooks": {
"SessionStart": [
{
"matcher": ".*",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/scripts/ensure-binary.sh"
}
]
}
],
"SessionEnd": [
{
"matcher": ".*",
"hooks": [
{
"type": "command",
"command": "claude-irc quit 2>/dev/null || true"
}
]
}
]
}
}
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 · 43 lines scan A 162ba2ea67d9
claude-irc is a plugin published in the GitHub repository bang9/ai-tools (10 stars, last pushed 1mo 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
agentrq-workspace
Workspace agent that executes tasks assigned by humans or supervisors, communicates progress via reply, and manages task lifecycle within a specific AgentRQ workspace.
agentrq
Human-in-the-loop task supervisor for AI agents.
supergoal
Plan and autonomously build a software task end-to-end. Recons the codebase, applies preloaded memory, decomposes into the right number of phases, gets one confirmation, then prepares a single ready-to-paste /goal command — one paste between you and done — that drives execution to completion with built-in retry…
context-graph-plugins marketplace
Runtime plugins for Agent Context Graph.
harness-maker
Per-project AI coding harness for Claude Code · Cursor · Codex. Profiler + 10-dim interview build a different harness for every project.
deadeye
Fits model, effort, and context to each task via a deterministic policy kernel behind Claude Code hooks. He doesn't waste shots.