---
name: differential-audit
description: Compare two implementations of the same thing — a port (R↔Python↔Stata), a reimplementation, a replication package, a refactor, or a new version against the old — so that agreement means something. Freeze inputs first, inventory every expected output, test the comparator itself, compare every channel (not just the headline number), and give each divergence a stable ID and a smallest witness. Use for cross-language parity, replication, upgrade/regression gates, or whenever "the numbers match" is about to license a claim.
---
<!-- Generated by scripts/sync-agent-skills.py from .claude/skills/differential-audit/SKILL.md. Do not edit: change the source and re-run the script. -->

# differential-audit

This skill's instructions live in [`.claude/skills/differential-audit/SKILL.md`](../../../.claude/skills/differential-audit/SKILL.md).
Read that file now and follow it, with the files it points to. Read [`AGENTS.md`](../../../AGENTS.md)
first if you have not already.

It was written for Claude Code. Running it from Codex, Antigravity or another agent:

- **Arguments.** Where it says `$ARGUMENTS`, use what the user asked for.
- **Claude Code agents.** Where a step hands work to an agent in `.claude/agents/` (through the
  `Agent` or `Task` tool), read that agent's file and do the step yourself after the main work.
  Tell the user the step was not an independent review: the same agent did both.
- **Claude Code settings.** `allowed-tools`, `model`, `effort`, `argument-hint` and
  `disable-model-invocation` in the source's frontmatter configure Claude Code. Ignore them.
- **Guards.** Claude Code's guard hooks do not run for you. Follow the rules in `AGENTS.md`
  yourself; the git pre-commit gate and CI still apply to your commits.
