# Maintenance agents DevPlace is **self-maintaining**. Alongside the site you use, a fleet of autonomous AI agents continuously reviews the codebase for security, audit coverage, documentation accuracy, and code quality, then fixes what it finds and proves the build still works. This page explains what the fleet is and what each agent does. The companion page, [Running the agents](/docs/maintenance-usage.html), shows exactly how to run them, with copy-paste commands. > New here? You do not need to know the codebase. Talk to **Maestro**, the > conductor, in plain language ("is my audit coverage complete?") and it runs the > right agent for you and explains the result. ## How it works in one minute - Each agent owns **one quality dimension** and sweeps the whole repository for problems in that dimension only. - Every agent has two modes: **check** (report only, changes nothing) and **fix** (correct the problem, then verify the build). - After any change, an agent runs a built-in **validator** (Python, JavaScript, CSS, and HTML/templates) plus an application import, and refuses to finish if the build is broken. - Every run writes a small **report** (a JSON file and a readable summary) so you can see exactly what was found and fixed. - Each agent runs **in isolation**: it only ever uses its own reviewing tools, so one agent can never trigger another or kick off the whole fleet by accident. Runs stay fast and predictable. - When you ask Maestro to review **everything**, it runs each agent **once** and remembers the results to answer your follow-up questions, instead of repeating the same work. ## Meet the fleet | Agent | What it watches | |-------|-----------------| | **Maestro** | The conductor you talk to. It picks the right agent (or the whole fleet) and explains the result. | | **Security** | Every route is correctly authorized; private data and admin actions are protected; user input is validated. | | **Audit** | Every action that changes data leaves an audit-log entry, including denials and failures. | | **Devii** | The Devii assistant can do everything the site offers for your role, and only shows tools your role is allowed to use. | | **Docs** | CLAUDE.md, AGENTS.md, README, and these docs pages stay in step with the code, shown to the right audience. | | **Feature completeness** | A new feature is wired all the way through: form, JSON schema, Devii tool, API docs, SEO, and README. | | **Duplication** | Shared helpers are reused instead of copy-pasted logic. | | **Style** | Naming, headers, typing, and formatting follow the project rules, applied with context so code that intentionally uses a pattern or character is left alone. | | **Frontend** | JavaScript modules, web components, and CSS follow the project's strict structure. | | **SEO** | Public pages carry the right search metadata and appear in the sitemap. | | **Tests** | Routes without an integration test get one written (the agent never runs the suite itself). | ## One directory they never touch The agents leave their own home alone. The `agents/` directory holds the agents' source, which deliberately contains the very patterns they search for (special characters, example bad names, dangerous command text) as **detection data**, not as mistakes. Scanning it would flag false problems, and fixing those would break the agents. So every agent run hard-blocks any change under `agents/`, and the agents are told never to read or scan it. The directory is off-limits to every checker and cleanup, by design. ## Why this exists A single feature in DevPlace touches many layers at once: a route is rendered as a page, served as JSON, exposed to the Devii assistant, written into the API docs, audited, and indexed for search. It is easy for a human to change one layer and forget a connected one. The fleet exists to catch exactly that, on every dimension, across the whole project, without anyone having to remember the full map. ## Where to go next - [Running the agents](/docs/maintenance-usage.html) - the commands, with examples. - [Devii Assistant](/docs/devii.html) - the in-app assistant the Devii agent keeps honest.