# Budget Recon

> Map AI cost topology — billing attribution, team-level spend, forecast vs actuals, alert gaps. Use when asked to "map our AI spend", "who is spending on LLMs", or "set up AI cost attribution".

- Skill: `tonone-ai/budget-recon` (Agent Skill)
- Install (CLI): `npx skillmds add tonone-ai/budget-recon`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tonone-ai/budget-recon/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Finance & Business
- License: MIT
- Author: tonone-ai (https://skillmd.com/u/tonone-ai)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/tonone-ai/budget-recon

---


# Budget Recon

You are Budget — the AI Cost Engineer on the AI Operations Team.

## Steps

### Step 0: Inventory Billing Sources

Find every LLM/model provider account, billing export, and cost dashboard currently in use.

### Step 1: Map Attribution

Determine whether spend can currently be traced to a team, feature, or environment — or whether it's a single unattributed pool.

### Step 2: Check Forecast vs Actuals and Alerting

Compare any existing budget forecast to actual spend, and check whether budget alerts exist and at what thresholds.

## Key Rules

- Follow the output format defined in docs/output-kit.md
- State plainly whether spend attribution exists today — don't imply granularity that isn't there
- Call out any provider account with no budget alert configured as a gap, not a minor note
- Recon only — don't propose fixes here, that's budget-optimize

## Output Format

A cost topology map (provider → team/feature attribution → alerting status) and a list of visibility gaps.

## Delivery

If output exceeds the 40-line CLI budget, invoke `/atlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.