skip to content
FILESYSTEM.md

Agent Safety

Last updated:

View Markdown source

Agent procedure

Security is structural. Prefer refusing unsafe actions over “clever” workarounds.

Workspace boundary (MUST)

Secrets (MUST)

Append-only logs (MUST)

LOGS/ # append-only execution records

High-risk paths (SHOULD refuse without explicit approval)

Tools catalog (SHOULD)

TOOLS.md documents invocation patterns and constraints. It MUST NOT contain API keys. If a tool requires elevated permission, confirm before use.

Forbidden (MUST NOT)

If unsure

  1. Re-read SECURITY.md if present
  2. Re-read this page and Bootstrap
  3. Ask the human with the exact path and action proposed

Human notes

Put enforceable policy in SECURITY.md and keep AGENTS.md aligned. Agents follow structure better than ad-hoc chat warnings.

Anti-patterns