Val Town now supports AGENTS.md. This is a feature we craved for ourselves and think you may find quite useful.
Per val #
When you include an AGENTS.md
file in any val, Townie will automatically read those instructions when viewing that val. Perfect for onboarding an agent to a project, explaining preferences and patterns and gotchas.
Per user #
For instructions and preferences that Townie should always be aware of, you
can add AGENTS.md
instructions in a special .config
val, which you can create and view via
val.town/settings/preferences.
Per org #
Orgs can also create agent instructions for context shared across your team.
Like your personal instructions, org-wide instructions live in AGENTS.md
within your org's .config
val, also accessible in org Settings > Preferences.
For any agent #
Agent instructions are surfaced to any agent—not just Townie—via our MCP server. So when you're using Claude Code, Codex, Cursor, or somesuch, your agent will have always read your personal instructions (and can likewise read per-org and per-val instructions).
Self-improving agents #
One neat thing about AGENTS.md
is that agents can read and write to the file. By writing its own instructions, an agent can create its own memory system.
This complements our
[custom skills](/changelog-2026-07-02#write-your-own-skills-for-townie) and
[platform skills](/plugin#capabilities) that agents can already discover. In
combination, instructions and skills make Val Town a malleable and durable space
for agents. Read more about agent instructions and skills in our documentation.
We're hiring!
Are you an infra engineer who cares about the joy of programming?