pi-auto — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited pi-auto (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
The pi-auto must be configured in pi's MCP config (e.g. ~/.pi/agent/mcp.json) so the following tools are available:
load-balancing or high-availability (from server config).load-balancing or high-availability. Persisted to server config.mcp_pi-auto_pi_get_usage. Optional input: period (default daily). Returns tokens and cost per backend.mcp_pi-auto_pi_get_provider. Optional: scope (global/project), projectPath. Returns pi's current defaultProvider and defaultModel.mcp_pi-auto_pi_get_strategy. Returns load-balancing or high-availability.mcp_pi-auto_pi_get_priority to see the ordered list of backends used when strategy is high-availability.mcp_pi-auto_pi_suggest_provider (optional input: period). It returns recommended provider and model for the current strategy.mcp_pi-auto_pi_set_provider with the suggested provider and model. Optional: scope (global/project), projectPath.mcp_pi-auto_pi_set_strategy with load-balancing or high-availability, and/or mcp_pi-auto_pi_set_priority with an array of backend ids (e.g. ["codex", "claude-code", "cursorai"]). Then optionally call pi_suggest_provider and pi_set_provider again.When the user asks to switch provider but does not specify a model, use these default models per provider:
| Provider | Default model |
|---|---|
| Cursor | auto |
| OpenAI | gpt-5.2-codex |
| Claude Code | claude-sonnet-4-6 |
Strategy and priority are stored in ~/.pi/agent/pi-auto.json. Valid backend ids: claude-code, codex, cursorai.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.