| FMRS | 34 / 100 · D | 79 / 100 · B |
|---|
| Reliability | 3 / 20 | 12 / 20 |
|---|
| Security and permissions | 8 / 20 | 18 / 20 |
|---|
| Maintenance | 11 / 20 | 16 / 20 |
|---|
| Documentation | 8 / 20 | 18 / 20 |
|---|
| Setup experience | 4 / 20 | 15 / 20 |
|---|
| Best for | - Teams that need to reuse agents, skills, commands, and rules across multiple AI coding platforms
- Complex projects lasting weeks or months that require project memory, quality gates, and auditability
- Developers who want to deploy plain-text AI artifacts through a CLI
| - 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 scripts, typo fixes, or code explanations that fit in a single conversation
- Users who require a confirmed MCP tool list, transport protocol, or client compatibility guarantee
- Users seeking an LLM runtime or a framework imported directly into an application
| - 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 | - Write agents, skills, rules, and context files to project- or user-level directories according to the selected platform and scope
- Project deployments may create or update .aiwg/ and platform-specific directories
- Optional native features may build dependencies such as node-pty or hnswlib-node
| - 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 | - Global user-scope deployment may cause context or agent sets to bleed across projects
- The README's quantitative claims, research findings, and performance statements are not independently verified by the supplied material
- Because the server manifest is unavailable, the MCP endpoint, tool permissions, authentication, and data-access scope cannot be confirmed
| - 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, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 0 | 0 |
|---|