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 anthropics/claude-plugins-officialnpx agentmods add plugins/anthropics/claude-plugins-official/imessagegit clone --depth 1 https://github.com/anthropics/claude-plugins-officialGrade A, and why
imessage 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- imessage — 100% identical, 0 lines differ
What it actually says
{
"name": "imessage",
"description": "iMessage channel for Claude Code \u2014 reads chat.db directly, sends via AppleScript. Built-in access control; manage pairing, allowlists, and policy via /imessage:access.",
"version": "0.1.0",
"keywords": [
"imessage",
"messaging",
"channel",
"mcp"
]
}
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 · 12 lines scan A ef21e0038966
imessage is a plugin published in the GitHub repository anthropics/claude-plugins-official (35,799 stars, last pushed today), 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
xcode-build-skills
A multi-skill plugin for benchmarking and optimizing Xcode builds, compile hotspots, project settings, and Swift Package Manager dependency overhead.
dev-gtm-claude-skills marketplace
Marketing and writing skills for Claude Code — analytics, ads, CRO, copywriting, blog writing, SEO, and more.
ralph-loop-template
Generate an iterable checklist PROMPT file for Ralph Loop from a plan file or the current conversation, and output the ready-to-run /ralph-loop command.
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…
skillctx
Make your agent skills portable by extracting hardcoded values into a central config and embedding resolver scripts.
auth
Auth skills for Claude Code — scaffold hand-rolled auth endpoints and audit auth code against security best practices.