What is deliverable-review?

A pre-delivery checklist for reviewing work before it is shown to a client. It covers requirements, tests, edge cases, error messages, visual details, and code cleanliness.

Use it when a feature or milestone is complete and needs a final client-readiness check.

It helps catch missing requirements, broken behaviour, unfinished interface states, and development leftovers before handoff.

deliverable-review — Skill for Claude Code and Codex by mizukaizen

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 mizukaizen/hive-doctrine-mcp --skill deliverable-review

Clone the repo

git clone --depth 1 https://github.com/mizukaizen/hive-doctrine-mcp

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mizukaizen/hive-doctrine-mcp/deliverable-review/github.svg)](https://agentmods.dev/skills/mizukaizen/hive-doctrine-mcp/deliverable-review)

Your own site

<a href="https://agentmods.dev/skills/mizukaizen/hive-doctrine-mcp/deliverable-review"><img src="https://agentmods.dev/badge/skills/mizukaizen/hive-doctrine-mcp/deliverable-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mizukaizen/hive-doctrine-mcp/deliverable-review"><img src="https://agentmods.dev/badge/skills/mizukaizen/hive-doctrine-mcp/deliverable-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 567 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00567
Opus 5.5	$0.00000	$0.00227
Sonnet 5.5	$0.00000	$0.00113
Haiku 4.5	$0.00000	$0.00057

Measured 2mo ago against content hash 1ee4fbd287a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deliverable-review 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 2mo 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.

gated-products/honey/claude-packages/HD-4002-agency-team/skills/deliverable-review/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Deliverable Review

Use when reviewing a deliverable before handing it off to the client. Checks quality, completeness, presentation, and readiness for client consumption.

Trigger

Invoke this skill when a feature or milestone is complete and ready for client review. Run this before every client-facing delivery.

Review Checklist

1. Acceptance Criteria

Read the original spec or user story
Verify each acceptance criterion is met
Flag any criteria that were modified during implementation (and ensure the client approved the change)

2. Functional Quality

Run the full test suite — all tests must pass
Test the happy path manually
Test at least 2 edge cases per feature
Verify error states show user-friendly messages (not stack traces or raw error codes)
Check loading states and empty states

3. Visual Quality

Compare implementation against design mockups (if provided)
Check responsive behaviour at 375px, 768px, and 1440px widths
Verify consistent spacing, typography, and colour usage
Check dark mode if applicable

4. Code Quality

No debug statements (console.log, print, debugger)
No commented-out code
No hardcoded values that should be configuration
No TODO comments without associated tracked issues
Dependencies are up to date and free of known vulnerabilities

5. Documentation

README includes setup and run instructions
API endpoints are documented (if applicable)
Environment variables are listed in .env.example
Any complex business logic has inline comments explaining "why"

6. Presentation

Demo script prepared (step-by-step walkthrough for the client)
Known limitations documented honestly
Next steps clearly outlined

Output

Generate a review report at clients/[client-slug]/docs/reviews/review-[YYYY-MM-DD].md:

# Deliverable Review: [Feature/Milestone]
**Date:** [YYYY-MM-DD]
**Reviewer:** [Name]

## Verdict: Ready / Needs Work / Blocked

## Acceptance Criteria: [X/Y] met

## Issues Found
| # | Severity | Description | Status |
|---|----------|-------------|--------|
| 1 | High     | [Issue]     | Open   |

## Recommendation
[Ship as-is / Fix issues first / Needs rework]

Read the full file on GitHub · 74 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.

2mo ago First seen · 74 lines · 0 tokens per session scan A 1ee4fbd287a1

Subscribe to this mod's changes

deliverable-review is a skill published in the GitHub repository mizukaizen/hive-doctrine-mcp (0 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 567 tokens. 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.

AI Safety Code review Multi-Agent agent-marketplace ai-agents mcp mcp-server

deliverable-review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
deliverable-reviewmizukaizen/hive-doctrine-mcp	Skill	0	4mo ago	MIT	A	0	Claude Code, Codex
java-best-practicesTaoidle/plan-cascade	Skill	133	7mo ago	MIT	A	32	Claude Code
release-pr-reviewcyanheads/shift-mcp-server	Skill	1	21d ago	Apache-2.0	A	136	Claude Code
code-simplifiercyanheads/shift-mcp-server	Skill	1	21d ago	Apache-2.0	A	160	Claude Code
issuejeremylongshore/tons-of-skills-marketplace	Skill	2.9k	today	MIT	A	115	Claude Code
link-checkjmagly/aiwg	Skill	229	yesterday	MIT	A	29	Claude Code, Codex
great_ctoavelikiy/great_cto	Skill	112	2d ago	MIT	A	32	Claude Code