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 amaar-mc/witnpx agentmods add plugins/amaar-mc/wit/marketplacegit clone --depth 1 https://github.com/amaar-mc/witGrade A, and why
wit-marketplace 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
{
"$schema": "https://code.claude.com/schemas/marketplace.json",
"name": "wit-marketplace",
"owner": {
"name": "Amaar Chughtai",
"email": "[email protected]"
},
"metadata": {
"description": "Wit — Agent Coordination Protocol. Prevents merge conflicts when multiple AI agents work on the same codebase.",
"version": "1.0.0"
},
"plugins": [
{
"name": "wit",
"source": {
"source": "github",
"repo": "amaar-mc/wit"
},
"description": "Coordinate multiple AI agents on the same codebase. Declares intents, locks symbols, detects conflicts — before code is written.",
"version": "0.1.0",
"author": {
"name": "Amaar Chughtai"
},
"homepage": "https://github.com/amaar-mc/wit",
"repository": "https://github.com/amaar-mc/wit",
"license": "MIT",
"keywords": [
"ai",
"agents",
"coordination",
"merge-conflicts",
"multi-agent",
"claude-code"
],
"category": "development"
}
]
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 39 lines scan A fe816853136b
wit-marketplace is a plugin published in the GitHub repository amaar-mc/wit (46 stars, last pushed 5mo 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
building-multiagent-systems
Architecture patterns for multi-agent systems with orchestrators, sub-agents, and tool coordination.
jenkins-cli
GitHub CLI-style interface for Jenkins controllers - create multibranch jobs, inspect config.xml, and manage runs, logs, artifacts, credentials, nodes, and queues.
claude-ops
Claude Code operations toolkit. Twelve skills: audit-skill-visibility (audit whether each installed skill is actually VISIBLE to the model, and diagnose why most of a fleet never gets used — a skill is invisible when its description is dropped by Claude Code's skill-listing context budget, which sheds descriptions…
aomi
Aomi for AI agents — drive the Aomi CLI from natural-language prompts (chat, simulate, sign on-chain transactions with account-abstraction-aware execution) and scaffold new Aomi apps from API specs. Bundle ships two skills: aomi-transact (run on-chain across 40+ DeFi/perps/CEX/social apps on EVM mainnets and L2s) and…
earthquake-mcp-server
Search USGS and EMSC seismic data — real-time feeds, event queries, and earthquake counts via MCP. STDIO or Streamable HTTP.
notifications
Cross-platform notifications when Claude Code needs user input.