Menu

Individual skill

northstar-payer-ops

Structure Northstar payer-operations outputs for authorization, appeals, claim repricing, peer-to-peer, and finance queue tasks. Use when a prompt references the shared Northstar environment, a target case/claim/appeal/queue ID, a task_context payload, and a required JSON answer template.

experiments/codex_gpt5_5_xhigh/reports/skills/task_group_014/self/self_attempt_01/SKILL.md

Read pinned source

Source commit 5082a777379156a048881e94940d640702e5e09a

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Instructions only
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
121
Repository last updated
Oct 29, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Northstar Payer Ops

## Workflow

1. Read `prompt.txt`, `payloads/task_context.json`, `payloads/answer_template.json`, and `environment_access.md` when provided.
2. Identify the target business IDs, reporting date or period, and the exact schema family.
3. Use the Northstar environment API with the provided bearer token, typically `POST /sql/query`, plus any listed business endpoints. Do not inspect local source or generated data files directly.
4. Pull current controlling records first. Prefer live case, claim, appeal, policy, document, authorization, rate schedule, or queue records over stale exports, distractor schedules, or incomplete references.
5. Build exactly one JSON object. Match the template shape exactly, use only declared values, preserve requested ordering, and keep numeric/date formats precise.
6. Fill any basis or audit trail with real record IDs only. Put controlling records first, then gap or exception records.
7. Return no markdown, prose, or code fences.

## Basis Precedence