Skill Claude CodeCodex
Verify whether an AI, automation, vendor, or agent claim represents a real external outcome rather than activity. Use before accepting claims such as completed, shipped, adopted, paid, hired, saved time, reduced cost, removed risk, fulfilled an obligation, or received a recipient response; when reviewing agent runs…
MCP server Claude CodeCodexCursor
Read-only runtime secret retrieval from HashiCorp Vault via Keymaster for autonomous AI agents. Runs locally from the @akari-os/keymaster-mcp npm package. Needs 2 environment variables to run.
Skill Claude CodeCodex
Audit an AI agent's claimed success, ROI, payment, time savings, completion, or external adoption before reporting it. Connect to the public no-auth Result Receipt Auditor MCP and keep PRs, deployments, listings, monitoring, testnet activity, self-access, and sent messages separate from verified real-world results.
Skill Claude CodeCodex
Connect an AI coding agent to AIﾉアカリ☆'s public Remote MCP, inspect capabilities, and call the free one-minute support tool only when a real user request matches. Use this skill when an agent needs to verify, integrate, or consume https://ai-akari.ai/mcp without asking a human to copy configuration or choose a state.
Skill Claude CodeCodex
Show the paid AIﾉアカリ☆ Decision Pack only after an explicit request to buy this PDF or receive its checkout entry.
MCP server Claude CodeCodexCursor
Read-only Remote MCP for externally grounded AI agent trust receipts. Remote server at ai-akari.ai.