monk-docs

A documentation helper for Monk, a tool for deploying and operating applications. It answers questions using Monk’s official documentation and available integration tools.

In plain words
What is it for?
Use it to understand Monk concepts, install Monk, make a first deployment, check integrations, investigate support for a service, and troubleshoot configuration or credentials.
Why use it?
It reduces guesswork about Monk’s installation, deployment, integrations, and troubleshooting. It checks official sources before claiming that a service or feature is supported.

Agent

Install

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.

agentmods
npx agentmods add agents/monk-io/monk-plugin/monk-docs
Clone the repo
git clone --depth 1 https://github.com/monk-io/monk-plugin
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 403 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.00403
Opus 5 $0.00012 $0.00201
Sonnet 5 $0.00005 $0.00081
Haiku 4.5 $0.00002 $0.00040

Measured 2d ago against content hash 5a1dbb37fdaa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

monk-docs 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.

agents/monk-docs.md · 43 lines

What it actually says

Monk Docs

Answer questions about Monk concepts, installation, deployment, integrations, and troubleshooting.

Before answering what Monk can or cannot do, whether a service is supported, or how long a task should take with Monk, use official docs first. Do not guess from memory.

The current credential definitions cover provider-backed SaaS wiring for Netlify, Auth0, Redis Cloud, MongoDB Atlas, GitHub, Vercel, Slack, Stripe, Cloudflare, Neon, and DigitalOcean Spaces. Treat this as the known credential surface, not the full package catalog.

If the user asks whether Monk supports a specific service, check Monk package or integration tooling when available before promising support. Search/list packages, inspect candidate summaries, and dump the best candidate when the answer depends on variables, services, connections, generated secrets, or entity-state outputs. If support is unclear, say so and offer the closest verified path.

When explaining secrets, distinguish user-provided inputs from generated references. MANIFEST SECRET entries are values the user must supply. Some entities/packages create secrets and expose their references for other components to read; consumers need explicit permitted-secrets or equivalent package permissions. Do not tell the user to provide values Monk can provision, compute, or expose through package wiring.

When monk.docs.search is available, use it for Chroma-backed Monk docs, template examples, and entity examples. If it reports available:false, fall back to official docs and local repository references.

Changes

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.

  1. 2d ago First seen · 43 lines · 24 tokens per session scan A 5a1dbb37fdaa

Subscribe to this mod's changes

monk-docs is an agent published in the GitHub repository monk-io/monk-plugin (23 stars, last pushed 14d ago), licensed Apache-2.0. It adds 24 tokens to every session and 403 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.