Auditor Executor Protocol — Development skill for Claude Code

Auditor/Executor Protocol

[](https://github.com/tBeltty/auditor-executor-protocol/actions/workflows/ci.yml) [](https://pypi.org/project/auditor-executor-protocol/) [](https://www.python.org/downloads/) [](https://opensource.org/licenses/MIT) [](https://github.com/astral-sh/ruff) [](https://mypy-lang.org/) [](pyproject.toml)

A two-role protocol for running multi-phase work through AI agents without the plan drifting into open-ended discussion and without "all tests pass" masquerading as verification.

The **Auditor** defines what "done" means and proves it independently. The **Executor** implements one numbered task at a time and logs command output. Neither role crosses into the other.

[`SKILL.md`](SKILL.md) specifies the protocol core; [`references/`](references/) holds the parts an agent loads only when it reaches that step (task and gate writing, handoff templates, Autonomous mode, failure modes and a worked example). `auditkit` is a zero-dependency Python CLI that automates scaffolding, drift linting, negative controls, status tallies, and installing the skill into your agent.

---

When to Reach for This

Prompting an agent, scanning a diff, and shipping when it looks right works well for exploratory scripts and prototypes.

That approach fails when late mistakes carry real costs:

• Financial calculations and balance transfers
• Authorization, tenant isolation, and permission boundaries
• Destructive database schema migrations
• Automated backgroun