Files
fermata/README.md
T
g4borg 97001e1544 chore: rename packages/ to crates/
Move all 29 workspace members from packages/<name>/ to crates/<name>/.
Updates: workspace Cargo.toml (members + path deps), justfile, root
CLAUDE.md, scripts/build/CARGO_INSTALL.md, docs/architecture/crates.md
(renamed from packages.md), structural references in docs/architecture
and docs/configuration, per-crate CLAUDE.md self-references. Historical
plans, reports, and building/ docs are left untouched.

No behavior change; just check-all stays green and fermata tests pass.
2026-04-30 21:58:57 +02:00

1.4 KiB

dirigent_fermata

𝄐 fermata — a fast, harness-agnostic guard that blocks AI coding agents from reading, writing, or executing things they shouldn't.

Reads .botignore (gitignore syntax) and an optional botignore.toml for advanced rules. Designed to be called from agent hooks, used as an MCP server (future), or consumed as a library.

Status

v0.1 — first releasable slice:

  • Library: Op, Decision, Policy::check, Policy::check_command, project-root walk-up, .botignore walker (via ignore), botignore.toml parsing, path identification heuristics.
  • CLI: fermata check <path>..., fermata hook --harness <name>.
  • Harness: Claude Code (PreToolUse) only.

Out of scope for v0.1: Codex, Gemini, MCP server, audit log, filesystem watcher.

Quick start

# As a CLI
fermata check --op read /path/to/.env
echo $?  # 1 if blocked, 0 if allowed

# As a Claude Code hook
fermata hook --harness claude < hook_payload.json

Configuration

.botignore (gitignore syntax, applies to read + write):

.env
.env.*
secrets/**

botignore.toml (per-op rules):

[read]
patterns = [".env*", "secrets/**"]

[write]
patterns = ["vendor/**", "*.lock"]

[bash]
deny = ["rm -rf /", "git push --force*"]
ask = ["rm:*", "mv:*"]
allow_prefixes = ["make test", "git checkout:*"]

See also

  • docs/tools/fermata.md — Dirigent integration plan
  • docs/workpad/brainstorm/fermata.md — full product spec