| FMRS | 65 / 100 · C | 79 / 100 · B |
|---|
| Reliability | 12 / 20 | 12 / 20 |
|---|
| Security and permissions | 10 / 20 | 18 / 20 |
|---|
| Maintenance | 12 / 20 | 16 / 20 |
|---|
| Documentation | 16 / 20 | 18 / 20 |
|---|
| Setup experience | 15 / 20 | 15 / 20 |
|---|
| Best for | - Teams that want a structured spec-driven workflow for AI-assisted development.
- Developers who need to visualize project progress in their IDE.
- Projects that require an approval process and task tracking for compliance.
| - Engineering teams scaling AI coding agents while controlling spend
- Platform teams that need auditable, rollback-aware agent execution records
- Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow
|
|---|
| Not for | - Quick prototypes or small projects that don't need a rigid specification process.
- Scenarios requiring full cloud deployment with user authentication and HTTPS (currently needs a reverse proxy).
| - Developers who just want a simple code-completion helper without run governance
- Teams unwilling to accept local JSONL run records with HMAC signing
- Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)
|
|---|
| Required permissions | - Read and write access to the project directory (e.g., the `.spec-workflow` folder).
- Network access: The web dashboard binds to `127.0.0.1:5000` by default, allowing local access only.
- Create and manage files for specs, tasks, approvals, and logs.
| - Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
- Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
- Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
- Execution of user-configured verifier commands (e.g. npm test)
|
|---|
| Risks and side effects | - Data exposure: If the dashboard is exposed to the network, it could be accessed without authorization; it is bound to localhost by default, but reverse proxy and firewall configurations must be cautious.
- Misuse: Since AI agents may execute commands automatically, the tool may perform unintended actions; it is recommended to use in a controlled environment.
- Dependency risk: Using npx may be subject to npm supply chain risks; keep the package version up to date.
| - Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
- Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
- Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
- Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries
|
|---|
| Supported clients | Claude Desktop, Claude Code, Augment Code, Cline/Claude Dev, Continue IDE, Cursor, OpenCode, Windsurf, Codex | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 0 | 0 |
|---|