# CASAN Claude Code adoption template (Plan-20)

Drop `settings.json` into the target repo as `.claude/settings.json` (the
installer does this). It wires the four Claude Code lifecycle hooks
(`UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `Stop`) to the CASAN agentic
bridge so a developer can type prompts normally while every certified turn still
carries an H1→H7 trace and an H6 record.

Claude Code shares these project settings across its CLI, official VS Code
extension, and JetBrains integration. Claude Desktop and claude.ai are separate
products and are not covered by this local project-hook integration.

- The hook command resolves the repo root via `$CLAUDE_PROJECT_DIR`, so **no
  machine-specific path is committed**.
- It invokes `.casan/casan-hook.py`. That bootstrap reads project config,
  resolves the pinned global harness, verifies its live hash, then dispatches
  the thin Claude renderer. The bridge **never runs a model**.
- This is a **`project_hook`** integration: strong for a trusted project, but a
  member who can edit `.claude/settings.json` can disable it. For organization
  enforcement use a managed/pinned deployment (`managed_hook`) — see
  `docs/casan/CASAN_AGENTIC_CLIENT_SECURITY.md`.

## Install (cross-platform)

```bash
cd <repo>
casan init --client claude --mode enforce
casan doctor --client claude
```

## Feature flags (environment)

| Variable | Default | Meaning |
|---|---|---|
| `CASAN_AGENTIC_BRIDGE_ENABLED` | `1` | Master on/off. |
| `CASAN_AGENTIC_ENFORCEMENT_MODE` | `enforce` via init | `observe` (telemetry-only) or `enforce`. |
| `CASAN_AGENTIC_INTEGRATION_MODE` | `project_hook` | `project_hook` / `managed_hook` / `casan_owned`. |
| `CASAN_AGENTIC_CLIENT_ALLOWLIST` | (unset) | Comma list; clients outside it are `observed_only`. |