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/agent-sdk-devgit clone --depth 1 https://github.com/anthropics/claude-plugins-officialGrade A, and why
agent-sdk-dev 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
3 near-identical copies found in the catalogue:
- agent-sdk-dev — 100% identical, 0 lines differ
- agent-sdk-dev — 100% identical, 0 lines differ
- agent-sdk-dev — 100% identical, 0 lines differ
What it actually says
{
"name": "agent-sdk-dev",
"description": "Claude Agent SDK Development Plugin",
"author": {
"name": "Anthropic",
"email": "[email protected]"
}
}
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 · 9 lines scan A 92391d726e50
agent-sdk-dev 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
qiushi-skill
Qiushi Skill: methodology skills for AI agents guided by seeking truth from facts, with Claude Code, Cursor, OpenClaw, Codex, OpenCode, and Hermes guidance.
ck
Cavekit — compressed spec-driven dev. Full loop (grill → spec → research → review → build) over one SPEC.md file: three core commands + four reach-for. Caveman encoding. Bug-to-spec backprop.
rune
67-skill mesh for Claude Code with runtime auto-discipline — native hooks (preflight/sentinel/completion-gate/quarantine) auto-fire at lifecycle boundaries. 248 mesh connections + 46 signals, adaptive routing, mesh analytics, MCP quarantine guidance, and project memory.
anycap
Multimodal capabilities for AI agents through the AnyCap CLI.
taches-cc-resources
Curated Claude Code skills and commands for prompt engineering, MCP servers, subagents, hooks, and productivity workflows.
jaiskills
Orchestration (insistir, constatar, remoto), prompting (metaprompt), knowledge compounding, file-based TODOs, and OpenAI tooling (askcodex, image-to-frontend) as one Claude Code plugin.