Auditor Executor Protocol — Development skill for Claude Code
A two-role Auditor/Executor protocol for multi-phase agent-executed work, plus a small CLI (auditkit) that scaffolds, lints, and negative-controls it.
How to install Auditor Executor Protocol
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open tBeltty/auditor-executor-protocol and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Auditor Executor Protocol does
A two-role Auditor/Executor protocol for multi-phase agent-executed work, plus a small CLI (auditkit) that scaffolds, lints, and negative-controls it.
Alternatives in Development
- Executor 24.1k ★
- Validate Plan — You are tasked with validating that an implementation plan was correctly executed, verifying all success crite 10k ★
- Mono Color Skill — One-ink editorial print image skill — warm paper, halftone photography, active negative space, and restrained 3k ★
README
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
Related Skills
Kads
KADS (KRUZZZZY's Agent Delegation Surface): assign any coding agent to each role (find, triage, fix, review, i
Autowonder Claude Executor
Open-source executor for AutoWonder community edition — the complete scheduler protocol surface (dispatch, rel
Paynow Integration Skill
Claude skill for the Paynow Zimbabwe payment gateway: PHP/Laravel, Node.js/Express and raw HTTP, plus a correc
Fluxa
Essential macOS system controls one click away in your menu bar — plus live Claude & Codex quota tracking with
Review Sequence
/review-sequence — Multi-role adversarial review protocol
Jobs Eval
Scoring-quality check. Build a small golden set of your own vacancies labelled fits / doesn't-fit, score them
Related Agents
Framework Auditor
Protocol for auditing the EITR codebase for multi-language stack discrepancies, architectural drift, template
Fora Benchmark
FORA-internal research agent (not a client-run teammate) — studies well-executed websites, Fortune 500 and pol
Dx Triggering Reviewer
Review description and triggering quality plus developer experience: would the model route to this artifact at