@ccdevkit/ccaudit 0.5.2 → 0.6.1

package/README.md

@@ -78,26 +78,55 @@ Review the code for:
 - **Check**: Single verification (one `.sh` or `.md` file)
 - **Audit**: Collection of checks (directory with `audit.yaml`)
 
-Checks run sequentially and stop at first failure.
+Checks run in parallel by default, respecting any declared dependencies.
 
 ## audit.yaml
 
-The `audit.yaml` file can optionally specify which checks to run:
+The `audit.yaml` file configures the audit:
 
 ```yaml
+cwd: ../..                   # Working directory for checks (relative to audit.yaml)
 checks:
   - ../shared/*              # All checks from shared/ directory
   - ../other-audit           # All checks from another audit (recursively)
   - ./check-custom.sh        # Specific check file
+  - file: ./check-slow.sh    # Object syntax with dependencies
+    dependencies:
+      - ./check-setup.sh     # Must complete before check-slow.sh runs
 ```
 
-Paths are relative to the audit directory. Wildcards (`*`, `?`, `[...]`) are supported.
+### Fields
+
+| Field | Description |
+|-------|-------------|
+| `cwd` | Working directory for all checks (absolute or relative to audit.yaml). Default: where ccaudit was invoked. |
+| `checks` | List of checks to run. Supports strings or objects with `file` and `dependencies`. |
+
+### Check Discovery
 
-**Check discovery behavior:**
 - **No `checks:` field**: All `.sh` and `.md` files in the audit directory are loaded (default)
 - **`checks:` with items**: Only the specified items are loaded (exclusive mode)
 - **`checks: []` (empty)**: No checks are loaded (audit runs nothing)
 
+Paths are relative to the audit directory. Wildcards (`*`, `?`, `[...]`) are supported.
+
+### Dependencies
+
+Checks can declare dependencies to control execution order:
+
+```yaml
+checks:
+  - ./setup.sh
+  - file: ./test.sh
+    dependencies: ./setup.sh          # Single dependency (string)
+  - file: ./integration.sh
+    dependencies:                      # Multiple dependencies (array)
+      - ./setup.sh
+      - ./test.sh
+```
+
+Checks with satisfied dependencies run in parallel. Dependent checks wait for their prerequisites to complete.
+
 ## Configuration
 
 Settings file: `.ccaudit/settings.json` (project) or `~/.ccaudit/settings.json` (global)
@@ -105,7 +134,8 @@ Settings file: `.ccaudit/settings.json` (project) or `~/.ccaudit/settings.json`
 ```json
 {
   "claudeCommand": "claude --local",
-  "claudeCommandSummary": "~/.local/bin/claude"
+  "claudeCommandSummary": "~/.local/bin/claude",
+  "maxRunners": 4
 }
 ```
 
@@ -113,6 +143,7 @@ Settings file: `.ccaudit/settings.json` (project) or `~/.ccaudit/settings.json`
 |---------|---------|-------------|
 | `claudeCommand` | `claude` | Command to invoke Claude CLI (supports arguments) |
 | `claudeCommandSummary` | `claude` | Command for internal summary operations (MCP haiku calls) |
+| `maxRunners` | `0` | Maximum parallel check runners. `0` = unlimited parallelism. |
 
 ## CLI Reference
 
@@ -123,6 +154,24 @@ ccaudit run <audit-name>    Execute an audit
 
 ccaudit list                List available audits
   -v, --verbose             Enable debug output
+
+ccaudit completion <shell>  Generate shell completion script
+                            Shells: bash, zsh, fish, powershell
+```
+
+## Shell Completion
+
+Tab completion is automatically installed when using npm. For manual setup:
+
+```bash
+# Bash
+ccaudit completion bash > /etc/bash_completion.d/ccaudit
+
+# Zsh
+ccaudit completion zsh > "${fpath[1]}/_ccaudit"
+
+# Fish
+ccaudit completion fish > ~/.config/fish/completions/ccaudit.fish
 ```
 
 ## Output Modes
@@ -163,6 +212,7 @@ Shell:
 #!/bin/bash
 # ---
 # name: check-name
+# requires: transcript  # Optional: skip if no transcript available
 # ---
 ```
 
@@ -170,10 +220,19 @@ Markdown:
 ```markdown
 ---
 name: check-name
-model: haiku  # Optional
+model: haiku           # Optional: haiku (default), sonnet, opus
+requires: transcript   # Optional: skip if no transcript available
 ---
 ```
 
+### Frontmatter Fields
+
+| Field | Applies to | Description |
+|-------|-----------|-------------|
+| `name` | Both | Check name (required) |
+| `model` | Agent only | AI model to use: `haiku` (default), `sonnet`, `opus` |
+| `requires` | Both | Requirements that must be met. Currently supports `transcript` to skip when running standalone (not as a hook). |
+
 ## Agent Check Behavior
 
 Agent checks run in read-only mode. They can use `Read`, `Glob`, `Grep`, and `Bash` (for read operations only).
@@ -206,5 +265,5 @@ Agent checks return structured JSON:
 
 ## Exit Codes
 
-- `0`: All checks passed
+- `0`: All checks passed (skipped checks don't affect exit code)
 - `1`: At least one check failed or error occurred

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ccdevkit/ccaudit",
-  "version": "0.5.2",
+  "version": "0.6.1",
   "description": "Audit tool for Claude Code projects - runs compliance checks on code and agent actions",
   "bin": {
     "ccaudit": "bin/ccaudit"