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 zebbern/agent-collabnpx agentmods add plugins/zebbern/agent-collab/marketplacegit clone --depth 1 https://github.com/zebbern/agent-collabGrade A, and why
agent-collab 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": "agent-collab",
"owner": {
"name": "zebbern"
},
"metadata": {
"description": "Delegate work from Claude Code to other AI coding agents: Codex (community fork with Windows fixes) and Cursor, plus a goal plugin for long-horizon project goals.",
"version": "1.3.2"
},
"plugins": [
{
"name": "codex",
"description": "Use Codex from Claude Code to review code or delegate tasks.",
"version": "1.0.6+fork.9",
"author": {
"name": "zebbern"
},
"source": "./plugins/codex"
},
{
"name": "cursor",
"description": "Use Cursor from Claude Code to review code or delegate tasks.",
"version": "0.5.3",
"author": {
"name": "zebbern"
},
"source": "./plugins/cursor"
},
{
"name": "goal",
"description": "Set a long-horizon goal in a project and advance it one increment at a time, delegating to Codex/Cursor.",
"version": "0.3.2",
"author": {
"name": "zebbern"
},
"source": "./plugins/goal"
}
]
}
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 · 40 lines scan A c197b7e6f97d
agent-collab is a plugin published in the GitHub repository zebbern/agent-collab (32 stars, last pushed 17d 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 2026-08-30.
Other plugins, from other repositories
safe-android-reverser
Sandboxed Android reverse engineering with semantic program indexing, XREF/CFG queries and structured network evidence through MCP.
unslop
Three anti-slop scanners in one bundle: a-unslop-text catches AI-diction and cadence tells in prose, a-unslop-code catches bugs and tutorial-shaped patterns in source, a-unslop-ui catches stock-default looks in web UI. Each ships a deterministic scanner plus a Build mode that heads off the tell before it ships. The…
lovstudio-cc-plugins
Plugin marketplace listing 1 plugin: lovstudio.
swift-performance-pro
Performance: Instruments, SwiftUI render cost, memory and retain cycles, launch time, lists.
claude-skills
S-Tier Staff Researcher — skills that help you operate at staff-researcher level. Proper workflows for polishing raw ideas, expressing them rigorously, and implementing them properly. Covers RPI (Research→Plan→Implement with Codex peer review), rigorous LaTeX authoring and review, paper refinement, TikZ/pgfplots…
ghostty-config
Manage Ghostty terminal config with AI-powered tools and domain knowledge.