ingest-messageslisted

# ingest-messages > **Runs under AGENTS.md.** These contracts bind without being restated here: Privacy Invariant (`current_base` never outbound), Honesty Firewall, Placeholder/Bracket Ban, Gate Write-back, Domain-Neutral Rule, Browser Automation Contract, Activity Pulse logging, Tracker verify+snapshot, and Sent-Clears-Draft. Inline reminders at point-of-use are intentional; standalone restatements point back to the relevant AGENTS.md section. ## STEP 0 — CONSENT GATE (hard stop) This is the highest ToS-exposure capability in the automation stack. Messaging automation most directly risks a platform's terms of service — the consent gate here is the most explicit in the system. Never open a browser or touch any platform until consent is confirmed. Run: ``` careerrat automation status --json ``` Inspect the `capabilities.messaging` entry. The applicable platforms are `linkedin` and `wellfound`. For each platform, `allowed: true` means all three conditions are simultaneously true: the `messaging` capability global switch is on, that platform's per-capability switch is on, and the platform's one-time ToS consent is recorded. This is the three-part AND from `mayRun()` in `src/core/automation/consent.mjs` — never re-derive it in prose. If **no platform** shows `allowed: true`, explain exactly how to opt in, then stop — do not open a browser: 1. Read the platform's terms of service yourself to confirm automated messaging reads are permitted. 2. Record consent: `careerrat