benchmark
2 registry entries were observed exposing a tool named benchmark — none of them flagged as a privileged capability.
Every row is point-in-time scan output, dated below. Forge has an observed tool surface for 12,336 of 40,577 scannable entries (30%) — an entry that has not been scanned cannot appear here, so absence from this list is not evidence that an entry does not expose this tool.
- v4.5.0↓ 322/wk
The context spine for AI coding agents. 9 built-in providers + mcpConfig plugin contract (wrap any MCP server in 10 lines), generic MCP-client aggregator (stdio), pre-mortem mistake-guard, bi-temporal mistake memory, Anthropic Auto-Memory bridge, SSE stre
ClaudeCursorCopilotGeministructural-code-graphclaude-code-hooksai-codingcontext-engineeringknowledge-graphcontext-spine - v1.0.2
Benchmark, memory, Big O analysis for AI agents
ClaudeCursorCopilotGeminimcp