verifying-before-shipping

verifying-before-shipping is a skill for Claude Code from redhuntlabs/wizard. It costs 27 tokens per session (927 once invoked), scanned A, original, MIT.

A verification checklist that runs before you say work is finished, shipped, published, or complete. It compares the result with the agreed acceptance criteria or definition of done.

In plain words
What is it for?
Use it before closing tasks, tickets, pull requests, documents, plans, or other completed work.
Why use it?
It reduces the risk of declaring success while specific requirements, tests, or other evidence are still missing.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the wizard plugin — 37 skills, 6 commands, 1 agent, 1 hook shipped together

Good fit Use it before closing tasks, tickets, pull requests, documents, plans, or other…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhuntlabs/wizard/verifying-before-shipping
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add redhuntlabs/wizard --skill verifying-before-shipping
Clone the repo
git clone --depth 1 https://github.com/redhuntlabs/wizard

Made for: Claude Code.

Or install wizard, the plugin that ships this one along with the rest of its 37 skills, 6 commands, 1 agent, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for verifying-before-shipping

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhuntlabs/wizard/verifying-before-shipping.svg)](https://agentmods.dev/skills/redhuntlabs/wizard/verifying-before-shipping)
Your own site
<a href="https://agentmods.dev/skills/redhuntlabs/wizard/verifying-before-shipping"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/verifying-before-shipping.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 927 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00027 $0.00927
Opus 5 $0.00014 $0.00464
Sonnet 5 $0.00005 $0.00185
Haiku 4.5 $0.00003 $0.00093

Measured 6d ago against content hash 7abf1db5d05d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

verifying-before-shipping scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

spells/work/verifying-before-shipping/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verifying Before Shipping

What this does

Forces a verification pass before any "this is done" declaration. Works for shipped code, sent docs, published posts, completed tasks, and finished plans.

When to use

  • About to mark a task done in a tracker
  • About to send a "this is shipped" message
  • About to close a ticket / PR / case
  • About to tell someone "all set"

What you bring (Inputs)

  • The work being declared done
  • The original definition of done (or an inferred one if none was set)

What you get (Output)

Either: confirmation the work is genuinely done (and a "done" declaration), or a list of the specific gaps that must close first.

How it works (Steps)

This is a discipline. The behavioral structure is: a non-negotiable rule (below), an excuses-and-counters table to defeat rationalizations, warning signs to spot the moment of risk, and a hard gate that fires before any "done" declaration. Apply the gate; verify each acceptance criterion against actual evidence; declare done only on a clean pass.

The non-negotiable rule

Before declaring any work done, run the verification — actually run it, do not assert it from memory.

Excuses and counters

If you think... Reality
"I just finished it, of course it works" Just-finished work has the highest bug density. Verify.
"I already manually checked everything" Manual checking is unreliable. Run the verification step.
"The user is in a hurry" The user is more in a hurry to not have a regression. Verify.
"It's a tiny change" Tiny changes break things in small ways that are hard to find later. Verify.
"I'll verify and ship in parallel" "In parallel" usually means "ship now and verify if there's a complaint." Verify first.
"Verification is overkill for this" Then you don't actually know it's done. Verify.

Read the full file on GitHub · 93 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 93 lines · 27 tokens per session scan A 7abf1db5d05d

Subscribe to this mod's changes

verifying-before-shipping is a skill published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 927 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.