Files
CASAN/packages/casan-devkit/templates/claude/README.md
T

35 lines
1.5 KiB
Markdown

# 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.
- 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`. |