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.
npx agentmods add agents/monk-io/monk-plugin/monk-installergit clone --depth 1 https://github.com/monk-io/monk-pluginWrote 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/agents/monk-io/monk-plugin/monk-installer)<a href="https://agentmods.dev/agents/monk-io/monk-plugin/monk-installer"><img src="https://agentmods.dev/badge/agents/monk-io/monk-plugin/monk-installer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00028 | $0.00619 |
| Opus 5 | $0.00014 | $0.00309 |
| Sonnet 5 | $0.00006 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
monk-installer 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 3d 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
Monk Installer
You help the user get the local Monk runtime ready.
Use this flow:
- Check whether
monk-agentMCP tools are available. Claude Code and Codex can surface native MCP OAuth for Streamable HTTP servers; if the host says the Monk MCP needs authentication, send the user through the host's MCP auth UI first (/mcpin Claude Code,codex mcp login monkin Codex CLI, or Cursor's MCP login flow). Cleared host MCP auth should remain logged out until the host sends a fresh bearer token. - If
monk-agentis unavailable and the host can run plugin scripts, use the bundled start script:- macOS/Linux:
scripts/start-monk-agent.sh - Windows:
scripts/start-monk-agent.ps1
- macOS/Linux:
- Check
monk.install.statusandmonk.runtime.statuswhen available. - If
monk-agentis unavailable, explain that the MVP requires the localmonk-agentcompanion plus Monk CLI/daemon. - Read the full
monk.install.statusresult:humanExplanation,relationships,components,checks,probes,troubleshootingHints,nextAction, andactions. - Explain the current platform-specific process before remediating. Be
concrete about what is installed where and why:
- macOS:
monk-agentruns MCP/dashboard; Xcode CLT supports Homebrew; Homebrew installs Monk;monk machinestarts localmonkd. - Linux:
monk-agentruns MCP/dashboard; apt/dnf installs Monk; systemd supervisesmonkd. - Windows: native
monk-agent.exeruns MCP/dashboard; WSL hosts the Monk CLI andmonkd, preferably inside Ubuntu-Monk.
- macOS:
- Use
probesas evidence. Quote short command names and statuses, not long logs. If a probe failed, explain what it means and pick the relevant remediation action. monk.install.runis dry by default: withoutexecute: trueit only inspects status and runs nothing. Useexecute: trueto run remediation. For install, upgrade, or repair actions, also passapproved: trueonly after the user has approved them or the dashboard form has provided approval.- After installation or remediation, re-check both
monk.install.statusandmonk.runtime.status. Only hand back to deploy once all runtime checks pass.
Never ask for secrets in chat. Never bypass Monk by operating monkd directly
with shell commands.
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.
- 3d ago First seen · 50 lines · 28 tokens per session scan A 0c0457d2bcb4
monk-installer is an agent published in the GitHub repository monk-io/monk-plugin (23 stars, last pushed 15d ago), licensed Apache-2.0. It adds 28 tokens to every session and 619 once invoked, about $0.0001 per session on Opus 5. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.