Audit Request — Security skill for Claude Code
Verify that a feature implementation satisfies the original request — reopen issues if incomplete or incorrect.
How to install Audit Request
Installs to ~/.claude/commands/language-operator-language-operator-audit-request.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/language-operator/language-operator/HEAD/.claude/commands/audit-request.md -o ~/.claude/commands/language-operator-language-operator-audit-request.md Restart Claude Code, or start a new session, for it to be picked up.
What Audit Request does
description: Verify that a feature implementation satisfies the original request — reopen issues if incomplete or incorrect
Inputs
$ARGUMENTS— one or more of:- Issue numbers filed by
/request:#100,#101 #102, or bare100 101 - A PR number:
pr 42or#42 - Empty: look back at conversation history for the most recent
/requestrun
- Issue numbers filed by
Directions
You are a strict QA reviewer. Your job is to verify that a feature was implemented **completely and correctly** — n
Alternatives in Security
- Review Artifact — Creates one polished, self-contained HTML artifact from review findings, audit notes, PR feedback, code review 652 ★
- Maestro Odyssey — Long-running iterative cycle — one entry, seven modes (debug improve planex review security defensive ui) 530 ★
- Tier 3 Code Refinement Report — Date: 2026-03-20 Status: ALL 54 FINDINGS IMPLEMENTED Scope: Full codebase (18 plugins, 888 files, ~266K lines) 222 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Review Audit
Review recently closed audit issues for implementation quality — reopen with comments if work is incomplete or
Pipeline Team
Orchestrates the full implementation pipeline (impl-plan -> impl -> audit -> fix -> merge) across multiple pre
UI Generate
Full UI pipeline: architecture plan → user approval → implementation → audit. Provide feature requirements as
Claudrunner
Autonomous AI coding agent: finds bugs and security holes, fixes your Jira, Trello, GitHub Issues or Linear ti
Module Redesign Pipeline
Claude Code skill: redesign an existing module to a top-1% bar, end-to-end (audit -> build -> motion -> live-v
Audit With Verification
Run a parallel-review-then-adversarial-verify audit on a URL, feature spec, or code path. Dispatches N reviewe
Related Agents
Implementation Verifier
Verify that an implementation satisfies the spec's properties and requirements through property-based testing,
Sub Agent Tester
PROACTIVELY used to verify that an implementation actually satisfies the Issue's acceptance criteria at runtim
Mp Alignment Auditor
Read-only, fresh-context audit of a merged masterplan plan against the ORIGINAL user request. Consumes goals.m