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 cyanheads/shift-mcp-servernpx agentmods add plugins/cyanheads/shift-mcp-server/shift-mcp-servergit clone --depth 1 https://github.com/cyanheads/shift-mcp-serverGrade A, and why
shift-mcp-server 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": "shift-mcp-server",
"version": "0.1.6",
"description": "Lightweight coordination layer for multiple AI agents working on the same codebase simultaneously.",
"author": {
"name": "cyanheads"
},
"homepage": "https://github.com/cyanheads/shift-mcp-server#readme",
"repository": "https://github.com/cyanheads/shift-mcp-server",
"license": "Apache-2.0",
"mcpServers": {
"shift-mcp-server": {
"command": "npx",
"args": ["-y", "@cyanheads/shift-mcp-server"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio"
}
}
}
}
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 · 21 lines scan A 058cb7a5e3a6
shift-mcp-server is a plugin published in the GitHub repository cyanheads/shift-mcp-server (1 stars, last pushed 10d 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
dibs
Coordinate with other AI agents through the Dibs board: see who is working on what across one machine or several, typed mailboxes between agents, directory claims, and new mail delivered into your session instead of polling for it.
sema
Content-addressed vocabulary protocol — shared meaning for AI agents.
agent-comm
Agent-to-agent messaging for AI coding agents — sessions, direct/broadcast/channel messages, shared state, real-time feed, and a file-coordination hook for parallel edits.
longgraph-skill
Long-horizon agent skill: durable loop-graph runs (executor + clean-context supervisor), verified gates, owner A/B/C cards. Works with Claude Code, Codex, Cursor, and Grok Build. Invoke /longgraph, /loop-converge, /loop-deliver, or /loop-research.
jaiskills
Orchestration (insistir, constatar, remoto), prompting (metaprompt), knowledge compounding, file-based TODOs, and OpenAI tooling (askcodex, image-to-frontend) as one Claude Code plugin.
team-shinchan
The Agent Harness for Claude Code — Guardrails, Observability, and Quality Gates for AI-Powered Development. 15 specialist agents with structured workflows, budget controls, analytics, and self-learning.