Delegated Work Audit — Security skill for Claude Code
Compare what a teammate or agent delivered in one or more PRs against what was asked in tickets, PR comments, and instructions.
How to install Delegated Work Audit
Installs to ~/.claude/commands/mschabow-agentic-sdlc-delegated-work-audit.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/mschabow/agentic-sdlc/HEAD/.claude/commands/delegated-work-audit.md -o ~/.claude/commands/mschabow-agentic-sdlc-delegated-work-audit.md Restart Claude Code, or start a new session, for it to be picked up.
What Delegated Work Audit does
name: delegated-work-audit version: 1.0.0 description: Compare what a teammate or agent delivered in one or more PRs against what was asked in tickets, PR comments, and instructions. Use when the user asks "did this deliver what I asked for", wants an asked-versus-delivered table, or suspects scope creep in someone's PRs. changelog:
- "1.0.0 (2026-10-03): Added to the sdlc-workflow plugin so it ships to every account from one source."
Delegated work audit
The user leads engineers w
Alternatives in Security
- Skill Coverage Audit — Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs 2.8k ★
- Portaljs Check Data Quality — Audit a local or remote tabular file (CSV/TSV) for common data quality issues 2.3k ★
- Pocketpaw — Your AI agent in 30 seconds 775 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Linear Implementation Audit
Check open Linear tickets against the code to find what is done, partly done, not started, or obsolete, then u
Review Audit
Review recently closed audit issues for implementation quality — reopen with comments if work is incomplete or
Harness Audit
Audit an existing Claude Code harness for configuration integrity (4-scope scan, JSON validity, anti-patterns,
World Model MCP
world-model-mcp is a signed audit memory server for AI coding agents, delivered as an MCP tool. Every event Ed
Site Evaluation
Claude Code skill: passive, non-intrusive evaluation of a live website across content, accessibility, UX, SEO,
Compete
Competitive X-Ray — compare your site against any competitor (tech stack, SEO, performance, security)
Related Agents
Kimi Ask
Use this agent when the user wants Kimi to answer a free-form question about the repository in prose — explain
OSS Watcher
Checks the user's open PRs and claim comments opened via /oss for new reviews, comments, CI failures and merge
Docstring Writer
Adds/refreshes docstrings and doc-comments for changed source in the orchestration deliver stage, then leaves