CALLE-AI/awesome-phone-call-agents

CALLE-AI/awesome-phone-call-agents

Agent Claude Code

MUST BE USED before every real-call test run, before demo runs, and before any batch of Round 1 or Round 2 calls is triggered. Invoke by providing the number of leads in the current campaign and the remaining call budget. Verifies projected call count, business-hours gating, and retry bounds.

CALLE-AI/awesome-phone-call-agents

Agent Claude Code

MUST BE USED before any Round 1 call batch is written or executed. Audits every code path that could place a call and verifies the pre-Round-1 consent/approval gate is enforced. Use this after implementing the client-approval flow and again after any change to main.py or caller.py that touches call dispatch.

CALLE-AI/awesome-phone-call-agents

Agent Claude Code

MUST BE USED after implementing the Script Generator module and after adding any client-edit UI. Also invoke after any change that touches how OSM data or CALL-E API response fields flow into goals or prompts. Checks for prompt injection paths from untrusted external content.

CALLE-AI/awesome-phone-call-agents

Agent Claude Code

MUST BE USED after capturing a real calle call status JSON sample, and again after writing R1 classification or R2 extraction code. Invoke by pasting the real raw JSON into the prompt. Checks every code path that parses CALL-E output against what the API actually returns.

CALLE-AI/awesome-phone-call-agents

Agent Claude Code

Use only near submission time (target: 48 hours before the September 14 2026 deadline). Re-fetches all official rules fresh — do not rely on cached knowledge. Checks the full submission package against every requirement and reports pass/fail per item. Do not invoke this during development — save it for the final…