Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.
Static reason
No blocking static signals were detected.
Trigger
User runs `tokz statusline enable`; pricing fetch occurs during normal CLI commands unless offline/cached.
Impact
A user-requested command can replace a Claude Code statusLine setting and cause Claude Code to invoke the package statusline command.
Mechanism
Explicit Claude Code status-line configuration and local usage-log analysis.
Rationale
The package is a local usage-reporting CLI, but its explicit statusline setup persists a command in Claude Code configuration and can replace an existing status line. This merits a warning under the configured policy, not a block.
Evidence
package.jsondist/cli.jsdist/statusline-4UN2Q6BT.jsdist/chunk-65BQE6TI.jsdist/Root-IVPGDV7M.js~/.claude/settings.json~/.tokz/litellm-prices.json~/.claude/projects~/.claude.json.mcp.json
Network endpoints1
raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json