Skip to main content
Get from zero to a configured repo and your first substrate check in about a minute.

1. Install

The plugin path is recommended for Claude Code and Codex — the guards auto-wire and there is nothing to merge. See Installation for the full matrix, including the symlink dev setup.

2. Configure a repo

1

Emit every tool's config

This emits AGENTS.md, CLAUDE.md, .gemini/settings.json, .aider.conf.yml, and the rest — plus the .gitattributes union-merge rule the ledger needs. Claude Code, Codex, Cursor, Gemini, Aider, Copilot, Windsurf, Zed, and Continue now read the same rules, each from its own native file.
2

Health-check the setup

A pass/fail check of installed tools, guards, MCP auth, and config drift.
3

Change a rule later

Edit source/rules.json (or drop a per-repo .forge/rules.json), then recompile:
sync is idempotent — it only rewrites what changed.

3. Run the pre-action gate

The substrate is the layer that runs before the model edits code. One command runs the whole gate:
On Claude Code the substrate runs on every prompt automatically via a UserPromptSubmit hook — advisory only, silent on clean tasks. Every other tool gets a native config rule plus 19 MCP tools it can call itself.
If forge substrate says ASK FIRST, ask the returned questions before editing. Read the predicted impacted files — the blast radius — before any mutating change.

4. Explore the extras

5. Day two: the ledger is learning

Everything the substrate learned on day one landed as claims in .forge/ledger/. This is proof-carrying memory — now it starts paying off:

Keep going

Read how the pre-action gate composes its stages into one verdict.