tachi: Command for Claude Code

User Input

$ARGUMENTS

Consider user input before proceeding (if not empty).

Step 0: Parse Flags

1. If $ARGUMENTS contains --output-dir <path>:

   • Set output_dir to the specified path
   • Strip --output-dir <path> from $ARGUMENTS (trim extra whitespace)

2. Default: output_dir = docs/security/

3. If $ARGUMENTS contains --version <tag>:

   • Set version_tag to the specified tag (e.g., v1.0.0)
   • Append version_tag to output_dir (e.g., docs/security/v1.0.0/)
   • Strip --version <tag> from $ARGUMENTS (trim extra whitespace)

4. Default: version_tag = none (outputs go directly to output_dir)

5. Remaining $ARGUMENTS is treated as the architecture file path.

6. Default architecture path: docs/security/architecture.md

7. Generate a unique run folder:

   • Compute timestamp: YYYY-MM-DDTHH-MM-SS (e.g., 2026-03-25T14-30-22)
   • Set parent_dir to the current output_dir value (before appending timestamp)
   • Append to output_dir: {output_dir}/{timestamp}/
   • This ensures each run produces output in a unique subfolder
   • Example: examples/agentic-app/test-output/2026-03-25T14-30-22/

8. Auto-detect baseline from previous runs (unless --baseline was explicitly provided):

   • List all subdirectories in parent_dir
   • Exclude the current run's timestamp directory
   • Sort remaining directories lexicographically descending (ISO timestamps sort naturally)
   • Check each directory (most recent first) for a threats.md file
   • If found: set baseline_path to that file
   • If none found: baseline_path = null (first run — stateless mode)
   • Display when detected:

     Baseline detected: {baseline_path}
     

Overview

Single-command entry point for tachi threat modeling. Validates prerequisites, invokes the tachi orchestrator agent against an architecture description, and writes the full output suite to the target directory.

Flow: Validate → Analyze → Report

Output suite:

• threats.md — structured threat model (7 sections + correlated findings)
• threats.sarif — SARIF 2.1.0 for CI/CD integration
• threat-report.md — narrative report with executive summary and remediation roadmap
• attack-trees/ — Mermaid attack tree per Critical/High finding