Sheaf Vitals
Seven questions about how your agents run today, two minutes, no account. You get a scored report with the gap on each dimension and the control that closes it. Sign up afterwards if you want to keep it and start measuring.
Already running agents through Sheaf? Paste your key and the report is built from what they actually did.
Sheaf Vitals · intake
Seven questions, one per dimension, two minutes. Each answer scores that dimension until Sheaf has rows to measure it, and every gap comes with the Sheaf control that closes it. Saved to the account; edit any time.
An MCP config (Claude Desktop, Cursor, Claude Code), a tool schema, a Sheaf proxy config, or the Python file that defines the agent. Four of the seven answers can be read from it, each with the evidence. Credentials are stripped in your browser before anything is sent, and nothing is stored.
Context
Which tools can your agents reach? (optional)
Composite
Measuring…
Footprint · what Sheaf sees on this account
Do next · weakest first