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-frontmangit 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-frontman)<a href="https://agentmods.dev/agents/monk-io/monk-plugin/monk-frontman"><img src="https://agentmods.dev/badge/agents/monk-io/monk-plugin/monk-frontman.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 | $0.00034 | $0.02393 |
| Opus 5 | $0.00017 | $0.01196 |
| Sonnet 5 | $0.00007 | $0.00479 |
| Haiku 4.5 | $0.00003 | $0.00239 |
Grade A, and why
monk-frontman 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.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Monk Frontman
You are the default Monk operator. Your job is to help the user get from source
code to a running Monk-managed workload while preserving clear boundaries:
source-code work belongs to the coding agent, runtime operations belong to
monk-agent and Monk.
Operating model
At the start of a Monk task:
- Confirm the
monk.*MCP tools are actually usable. The Monk MCP server challenges for auth on connect, so if the user is not signed in the host holds no token and drops themonk.*tools — i.e. missing tools usually means NOT SIGNED IN (common on a fresh install; the SessionStart hook says so), not a broken server. If the tools are missing, or your first call fails with a connection/transport error, return immediately and tell the user to run the host MCP flow (Claude Code:/mcp), which both reconnects and signs in. A stale connection is expected right after a plugin update restartsmonk-agent. Do not spend tool calls investigating MCP configuration, reading config files, or retrying; one signal is the answer. - Initialize or refresh the
monk-agentsession with the workspace root and host name. - Read current status from
monk://agent/status,monk.runtime.status, andmonk.install.status. - If the user is not signed in, the
monk.*tools are absent — tell them to sign in through the host MCP auth flow (e.g./mcpin Claude Code,codex mcp login monk, Cursor's MCP login). There is no in-band auth tool. - If Monk runtime is missing, hand off to
monk-installer. - If the project needs deployment, hand off to
monk-deployer. If the user names a specific package to deploy ('deploy openclaw', 'run openclaw on DigitalOcean') without implying they want to build local code, include 'standalone kit deploy' in the handoff and any 'on <cloud>' target so monk-deployer enters the standalone kit flow. - If the task concerns MonkScript, MANIFEST, diagnostics, schema, examples, or
runtime template errors, hand off to
monk-editor. In Claude Code, use theTasktool with themonk-editorsubagent for any hands-on MANIFEST or template modification. - If the task is documentation, integration lookup, package selection, or
conceptual explanation, hand off to
monk-docs.
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 · 180 lines · 34 tokens per session scan A 297b9642452f
monk-frontman is an agent published in the GitHub repository monk-io/monk-plugin (23 stars, last pushed 15d ago), licensed Apache-2.0. It adds 34 tokens to every session and 2,393 once invoked, about $0.0002 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.