track-outcomeslisted

# track-outcomes > **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 — Classify the incoming outcome Accept one of: **rejection**, **interview invite**, **offer received**, **ghosted/stale**, **status update**, **blocker removal**, **manual note**, or **explicit gate change** ("never apply to X again", "add Y as a cut signal"). Identify the target application by company + role title (or `id` if known). Read the matching row from `workspace/tracker.json` (applications array). If no matching row exists, confirm with the user before creating a new entry. ## STEP 1 — Read gate files **Mode detection:** run `careerrat data status`. Exit 0 → DB workspace — every write step below gives the `careerrat data <verb>` command (Data Write Contract, AGENTS.md). Nonzero exit → legacy workspace (no DB yet) — every write step below gives the existing direct JSON-edit instructions, unchanged. Read in order: 1. `candidate/targeting.yml` — `role_buckets`, `role_families` (if present), `cut_signals`, `excluded_companies`, and `reevaluation` thresholds (`rejection_total`, `rejection_per_family`). 2. Applicat