Navigate the docs

SafeClaw Docs

A systematic tour of SafeClaw, one module per page. Concepts explain how the product thinks; guides get a task done; security answers the questions that decide trust. reference/ holds the lookup layer; contributor design docs live outside this tree in design/. Pages are deliberately short and will deepen over time.

New here? Read Overview, then do the Quickstart.

Concepts

PageThe module
OverviewThe whole model on one page: phantoms, the broker, passkey approvals
VaultWhere credentials live: sealed under your passkey, synced blind
ConnectionsThe catalog, host anchors, and how a secret becomes a phantom
Brokersc run: one local egress point that swaps phantoms for values
Approvals & policyWho decides what runs: levels, rules, single-use grants
AgentsAgent identities: attribution without possession

Guides

PageThe task
QuickstartZero to first brokered call in five minutes
sc run and phantomsThe patterns, and the sc get anti-pattern
For your agentHanding SafeClaw to an agent: skill file, paste-ready prompt

Security

PageThe question
Design principlesThe rules the whole system is built on
Security modelWhere keys live, what the cloud sees, what compromise costs

Reference

For users and service authors, in reference/: services.md (writing a service.toml), policy.md (per-action decisions), diagnostics.md (every error code, with fixes), consent-templates.md (approval-copy grammar).

Design docs

For contributors reading the source, outside this tree in design/: protocol.md (SUDP cryptographic profile), credential-broker.md (the broker architecture), connection-schema.md (vault data shapes), sync.md / sse-sync.md (cloud sync), request-scope.md (approval scope binding), stores-and-items.md (stores and vault content model).