| FMRS | 36 / 100 · D | 79 / 100 · B |
|---|
| Reliability | 5 / 20 | 12 / 20 |
|---|
| Security and permissions | 6 / 20 | 18 / 20 |
|---|
| Maintenance | 8 / 20 | 16 / 20 |
|---|
| Documentation | 7 / 20 | 18 / 20 |
|---|
| Setup experience | 10 / 20 | 15 / 20 |
|---|
| Best for | - Projects using Ruby and Bundler, where AI agents need to perform code checks, dependency management, or script execution.
- AI integrations where token savings are important.
| - 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 | - Simple Ruby script execution when structured output is not needed.
- Interactive Ruby sessions (e.g., IRB).
- MCP environments that do not support stdio transport.
| - 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 | - Execute Ruby and Bundler commands.
- Read gem installation directories, Gemfile, and related files.
- May create or modify gem-related files (e.g., during gem install).
- Network access (if installing gems from remote repositories).
| - 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 | - Executing arbitrary Ruby commands could lead to code execution risks; improper use by agents may cause security issues.
- Gem installation may modify the system environment; permissions must be used carefully.
- Tool output may contain sensitive information (e.g., gem versions) that should be protected.
- Supply chain risk: if the supply chain is compromised, installed gems could be unsafe.
| - 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, Cursor, VS Code, Windsurf, Cline / Roo Code, Codex, Gemini CLI, Zed, Continue | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 8 | 0 |
|---|