| FMRS | 67 / 100 · C | 79 / 100 · B |
|---|
| Reliability | 10 / 20 | 12 / 20 |
|---|
| Security and permissions | 13 / 20 | 18 / 20 |
|---|
| Maintenance | 14 / 20 | 16 / 20 |
|---|
| Documentation | 16 / 20 | 18 / 20 |
|---|
| Setup experience | 14 / 20 | 15 / 20 |
|---|
| Best for | - Developers who need AI assistants to understand local or remote codebases.
- Code-analysis workflows that need control over token counts and file scope.
- Users of Claude Desktop, VS Code, Cline, Cursor, or Claude Code.
| - 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 | - Users needing database, cloud-storage, or browser-automation capabilities.
- Workflows requiring direct codebase modification or general write operations.
- Users needing authentication, private-repository access, or capabilities not documented in the supplied material.
| - 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 the specified local directories and files.
- Fetch, clone, and process the specified GitHub repositories.
- Access existing Repomix output files.
- Run Secretlint-sensitive-data checks; remote configuration is not loaded unless explicitly trusted.
| - 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 | - Packed content may contain sensitive information; despite Secretlint checks, review outputs before sending them to AI tools.
- Remote repository configuration is untrusted by default; enabling trust may run external processing commands defined in configuration.
- Large repositories may exceed AI-tool file-size or context limits and require filtering, compression, or output splitting.
| - 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, VS Code, Cline, Cursor, Claude Code | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 7 | 0 |
|---|