agentwheelCAUTION
Skills, rules, and instructions across every AI agent. One source, every agent.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
agentwheel
One source. Every agent.
Weave skills, rules, instructions, commands, subagents, MCP, hooks, settings, and plugins across every AI agent you use, from any source, reconciled into each runtime with your private tweaks intact.
Why agentwheel?
Your AI agents are multiplying. OpenClaw, Claude Code, Codex CLI, Copilot, Hermes — and the next harness your team adopts. Each one wants its own skills, rules, instructions, commands, subagents, MCP servers, hooks, and settings, in its own layout.
agentwheel makes that one declared state. Add packages to .agentwheel/config.json, preview the runtime changes, then install the declared state into each target. Updates move tracking sources forward explicitly; installs make the current declaration true.
npm i -g agentwheel agentwheel init agentwheel add github:your-org/agent-pack --adapter codex --local --mode tracking agentwheel plan agentwheel install
No lock-in. No central gatekeeper. Packages live in plain git repos or local folders, customizations live in your workspace, and runtimes stay generated output.
Install Methods
CLI install
npm i -g agentwheel agentwheel init
Prefer pnpm? pnpm add -g agentwheel works too.
AI agent handoff
Give an agent install.md when you want it to install Agentwheel, verify the CLI, install the companion skill, and show the right catalogue flow for your runtime.
curl -fsSL https://raw.githubusercontent.com/NestDevLab/agentwheel/main/install.md
Companion skills
The management skill keeps Agentwheel commands and safety rules inside the runtime you are using. Install the discovery skill separately when you also want proactive, non-installing suggestions:
agentwheel doctor --adapter codex --local agentwheel install
5b3208b48757OBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add agentwheel --env AGENTWHEEL_AUTH_CONFIG=${AGENTWHEEL_AUTH_CONFIG} -- npx -y [email protected]{
"mcpServers": {
"agentwheel": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"AGENTWHEEL_AUTH_CONFIG": "${AGENTWHEEL_AUTH_CONFIG}"
}
}
}
}Exposed tools (5)
5 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
ai-agent | read | Build a conversational agent |
code-review | read | A |
inbox | read | C |
self-improve | read | Capture corrections for future sessions |
self-improving-agent | read | Continuously evolve from experience |
Trust audit
CAUTIONgrade B · trust 87/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (6 observation(s))
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (16)
identityFile: "~/.ssh/id_ed25519",
.nojekyll
identityFile: ".ssh/id_ed25519",
identityFile: join(project, ".ssh/id_ed25519"),
import type { Artifact } from "../../model/artifact.js";import type { Artifact } from "../../model/artifact.js";import { pathExists } from "../../utils/fs.js";import type { Artifact } from "../../model/artifact.js";import type { Artifact } from "../../model/artifact.js";process.env.ODOO_SERVICE_MCP_URL = "http://192.168.1.107:3201/mcp";
url: "http://192.168.1.107:3201/mcp",
expect(refreshed.mcp.servers["odoo-service"].url).toBe("http://192.168.1.107:3201/mcp");url: "http://192.168.1.107:3201/mcp",
url: "http://192.168.1.107:3201/mcp",
const artifact = await skillArtifact(`${validFrontmatter}`);mermaid
Gates applied: no_behavioural_pass.
5b3208b48757full audit observations/trust-audit/mcp-server/nestdevlab__agentwheel.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | 5b3208b48757 | CAUTION | B | 87 | first audit |
Questions
What is the agentwheel MCP server?
Skills, rules, and instructions across every AI agent. One source, every agent.
What tools does agentwheel expose?
5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is agentwheel safe to connect to an agent?
With care. The audit graded it B (87/100) and found 16 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does agentwheel need?
It reads AGENTWHEEL_AUTH_CONFIG from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does agentwheel run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as agentwheel at 0.20.20.
How current is this page?
The grade is for one exact copy of the source (5b3208b48757), read on 2026-10-12. The repository is watched and re-audited when it changes.