| FMRS | 57 / 100 · C | 79 / 100 · B |
|---|
| Reliability | 9 / 20 | 12 / 20 |
|---|
| Security and permissions | 8 / 20 | 18 / 20 |
|---|
| Maintenance | 14 / 20 | 16 / 20 |
|---|
| Documentation | 14 / 20 | 18 / 20 |
|---|
| Setup experience | 12 / 20 | 15 / 20 |
|---|
| Best for | - Coding agents that need IDE-level code understanding
- Large or complex multi-file projects
- Developers using MCP-enabled terminal clients, desktop clients, or IDEs
| - 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 | - Non-coding tasks
- Small tasks requiring only simple text edits
- Environments unwilling to grant project editing or shell-command capabilities
| - 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 | - It needs access to project files for code retrieval and editing.
- When basic tools are enabled, execute_shell_command can run shell commands such as builds, tests, and linters.
- The language-server backend may require additional dependencies for particular programming languages.
- The JetBrains backend requires the Serena JetBrains Plugin, which is paid and has a free trial.
| - 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 | - Symbolic edits, refactorings, and text replacements can modify or delete code.
- When shell tools are enabled, the agent can run builds, tests, linters, or other commands.
- Language-server support and capabilities vary by language.
- The JetBrains backend does not support Rider or CLion.
| - 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 Code, Codex, OpenCode, Gemini CLI, VS Code, Cursor, Claude Desktop, Open WebUI, JetBrains IDEs | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 6 | 0 |
|---|