Skip to content
Agentmart
Submit a tool

pre-delivery-audit

Final audit before delivering code or a system to a client.

Skill by G4rb4sh

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/g4rb4sh-pre-delivery-audit

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Final audit before delivering code or a system to a client. Use when the user says "let's deliver", "delivery audit", "is this ready for the client?", or before a handoff.

Use cases: security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/pre-delivery-audit

What's inside

Skill name
pre-delivery-audit
Description
Final audit before delivering code or a system to a client. Use when the user says "let's deliver", "delivery audit", "is this ready for the client?", or before a handoff.
License
MIT
Instructions
25 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

Review the full repo and report by section, with file:line
for each finding and severity (blocking / recommended):

1. Secrets and sensitive information: hardcoded credentials, committed .env
   files, real client data in fixtures, tests, seeds, or
   documentation, internal URLs that should not be exposed.
2. Git history: secrets or sensitive data in old commits
   (search history, not only HEAD).
3. Licenses: dependencies with licenses incompatible with the client's
   commercial use (GPL and similar); list the license for each
   direct dependency.
4. Declared debt: run the ponytail-debt skill (debt:,
   ponytail:, and FIXME markers); classify each row as "resolve before
   delivery" vs "document in the handoff".
5. Complexity: run ponytail-audit in repo mode and attach its
   result.
6. Operability: README with verified setup from scratch, documented
   environment variables, and up-to-date docs/HANDOFF.md (handoff skill).
7. Hygiene: dead code, temporary files, relevant unmerged branches,
   green CI configuration.

Close: verdict (ready / not ready) with blocker list. Do not
apply fixes automatically: report first and get confirmation.

From G4rb4sh/MLE-setup, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 30, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from G4rb4sh

Cite this page

pre-delivery-audit skill. Agent Mart. https://agentmart.dev/skills/g4rb4sh-pre-delivery-audit (last updated 2026-10-24)