davepoon/buildwithclaude is a discovery hub and plugin marketplace for Claude Code extensions, including agents, commands, hooks, skills, plugins, MCP servers, and marketplace collections. Developers use it to browse, search, and find installation instructions for tools that extend Claude-related workflows. Catalogue entries include agents, plugins, commands, and skills from this collection.
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.
git clone --depth 1 https://github.com/davepoon/buildwithclaudeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/davepoon/buildwithclaude/aigent-os)<a href="https://agentmods.dev/plugins/davepoon/buildwithclaude/aigent-os"><img src="https://agentmods.dev/badge/plugins/davepoon/buildwithclaude/aigent-os.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
aigent-os 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": "aigent-os",
"version": "1.1.0",
"description": "The session-lifecycle commands from aigent-OS, the open-source Claude Code operating system: /open (boot the session — load memory from the vault, surface what changed and what's blocked) and /close (bank the session back to memory so the next /open resumes with full context). Both skills declare scoped allowed-tools and run a vault-root preflight that verifies the configured aigent-OS vault before any write or script execution. Assumes the aigent-OS vault structure; see the repo and the plugin README for the full system and the security model.",
"author": {
"name": "wrg32786",
"url": "https://github.com/wrg32786"
},
"repository": "https://github.com/wrg32786/aigent-os",
"license": "MIT",
"keywords": [
"skills",
"aigent-os",
"session-management",
"persistent-memory",
"context-loading",
"open",
"close",
"obsidian-vault",
"claude-code-os"
]
}
What it installs
The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 31 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 23 lines scan A 6346e5bcfbb5
aigent-os is a plugin published in the GitHub repository davepoon/buildwithclaude (3,421 stars, last pushed today), 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 2026-09-05.
Other plugins, from other repositories
bedrock
Second Brain automation for Obsidian vaults — entity management, ingestion, compression, and sync via Claude Code skills.
archcore
Spec-driven development and context engineering for AI coding agents, backed by project context in Git.
pm-productivity
Session and context management: session init, handoff documents, context compaction, parallel task orchestration.
engram
Durable, local-first graph memory for AI coding assistants: decisions with reasons, gotchas, conflicts — inspectable and editable in a graph pane.
claude-reflect
Self-learning system for Claude Code that captures corrections and updates CLAUDE.md automatically.
context-mcp
Persistent AI memory + codebase knowledge graph MCP server for Claude Code.