# caveman-stats

Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.

## Decision Card

- Recommendation score: 47/100 (Needs evidence)
- Fit score: 57/100
- Trust tier: Needs review
- Install readiness: MCP ready
- Trial status: not_recorded
- Claim status: Unclaimed
- Verified level: Unverified
- Primary risk: No community evaluation
- Next action: collect_evidence

## Fit & Capabilities

- Role: Coding & Development
- Protocols: mcp, http, cli
- Capabilities: Coding assistance, MCP integration, Reusable skill package

## Evidence

- Source: https://mcpservers.org/agent-skills/juliusbrussee/caveman-stats
- Source activity: Source review needed
- Community reviews: 0
- External reputation signals: 0
- Known gaps: community review, third-party review/discussion signal, sandbox trial result

## Risk & Safety

- Security verdict: Install path is visible, but review permissions and run a sandbox task first.
- Required checks: Verify install source, Confirm license, Review permissions, Collect user evaluation

## Installation

- Readiness: MCP ready
- Primary method: MCP template
- Install JSON: https://agentstaffer.com/skills/mcpservers-caveman-stats/install.json

## Trial Plan

- Task: Run a small code review trial
- Expected output: A concise review with reproducible findings, changed-file scope, and test suggestions.
- Trial JSON: https://agentstaffer.com/skills/mcpservers-caveman-stats/trial.json

## Profile Data Package

- profile.json: https://agentstaffer.com/skills/mcpservers-caveman-stats/profile.json
- score.json: https://agentstaffer.com/skills/mcpservers-caveman-stats/score.json
- evidence.json: https://agentstaffer.com/skills/mcpservers-caveman-stats/evidence.json
- trust.json: https://agentstaffer.com/skills/mcpservers-caveman-stats/trust.json
- trial.json: https://agentstaffer.com/skills/mcpservers-caveman-stats/trial.json
- install.json: https://agentstaffer.com/skills/mcpservers-caveman-stats/install.json
- history.json: https://agentstaffer.com/skills/mcpservers-caveman-stats/history.json
- similar.json: https://agentstaffer.com/skills/mcpservers-caveman-stats/similar.json
- dossier.md: https://agentstaffer.com/skills/mcpservers-caveman-stats/dossier.md
- summary.md: https://agentstaffer.com/skills/mcpservers-caveman-stats/summary.md
- mcp.json: https://agentstaffer.com/skills/mcpservers-caveman-stats/mcp.json
- visibility-report.json: https://agentstaffer.com/vendors/mcpservers-caveman-stats/visibility-report.json
- claim.json: https://agentstaffer.com/claim.json
- Vendor visibility report: https://agentstaffer.com/vendors/mcpservers-caveman-stats/visibility-report
- Agent index: https://agentstaffer.com/agents.json