agentmods.dev

final-review

final-review is a skill for Claude Code from karsten-s-nielsen/mad-scientist-skills. It costs 80 tokens per session (3,166 once invoked), scanned A, original, MIT.

A pre-commit quality check for code and documentation. It reviews consistency, completeness, project conventions, and architecture diagrams before changes are committed.

In plain words
What is it for?
Use it before committing or pushing changes, after a feature or major refactor, or when you need a broad project review.
Why use it?
It catches unfinished work, documentation drift, and mismatches between the code and its described architecture.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the mad-scientist-skills plugin — 11 skills, 4 commands shipped together

not rated 3repo changed 1mo ago A scan 80 tokens original MIT

Good fit Use it before committing or pushing changes, after a feature or major refactor, or when you need a broad project review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/karsten-s-nielsen/mad-scientist-skills/final-review
View source ↗ karsten-s-nielsen/mad-scientist-skills
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 karsten-s-nielsen/mad-scientist-skills --skill final-review
Clone the repo
git clone --depth 1 https://github.com/karsten-s-nielsen/mad-scientist-skills

Made for: Claude Code.

Or install mad-scientist-skills, the plugin that ships this one along with the rest of its 11 skills, 4 commands.

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 final-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/final-review/github.svg)](https://agentmods.dev/skills/karsten-s-nielsen/mad-scientist-skills/final-review)
Your own site
<a href="https://agentmods.dev/skills/karsten-s-nielsen/mad-scientist-skills/final-review"><img src="https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/final-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.

agentmods 80×15 button for final-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/karsten-s-nielsen/mad-scientist-skills/final-review"><img src="https://agentmods.dev/badge/skills/karsten-s-nielsen/mad-scientist-skills/final-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,166 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 $0.00080 $0.03166
Opus 5.5 $0.00032 $0.01266
Sonnet 5.5 $0.00016 $0.00633
Haiku 4.5 $0.00008 $0.00317

Measured 1mo ago against content hash 1a75437b4676, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

final-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 1mo 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.

plugins/mad-scientist-skills/skills/final-review/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Final Review

A comprehensive pre-commit quality gate that ensures code, documentation, and architecture diagrams are consistent, complete, and follow professional standards.

When to use this skill

  • Before committing or pushing changes
  • After completing a feature or significant refactor
  • When the user says "final review", "check everything", "make sure it's all up to date", or "review before commit"
  • Periodically to catch documentation drift

Review process

Execute all phases in order. Do NOT skip phases. Do NOT claim completion without evidence.

Phase 1: Codebase Discovery

Explore the project to understand its current state:

  • Read the project's CLAUDE.md, AGENTS.md, README.md, and any other root-level documentation
  • Identify the tech stack, project structure, and architectural patterns
  • Note the testing framework and how tests are run
  • Identify all configuration files (package.json, pyproject.toml, tsconfig.json, etc.)

Phase 2: Code Quality Review

Review all source code as a professional software architect:

  • Consistency: Naming conventions, file organization, import patterns, error handling patterns
  • Best practices: SOLID principles, DRY, proper error handling, security (OWASP top 10)
  • Dead code: Unused imports, unreachable code, commented-out blocks, orphaned files
  • Type safety: Missing types, any usage, incomplete interfaces
  • Dependencies: Unused dependencies, outdated versions with known vulnerabilities
  • Tests: Coverage gaps, missing edge cases, outdated test assertions
  • Optimization claims: if a change claims a byte-identical / no-flip optimization, confirm the parity/oracle gate ran at production scale (not a smoke sample) and any behavior-changing part was separated out with its own record — a correctness fix cannot be byte-identical (mirrors optimization-audit P19 / ADR-004)

For deeper analysis, run the specialized audit skills from this plugin:

  • security-audit — STRIDE threat modeling, infrastructure hardening, supply chain audit, secrets scanning
  • observability-audit — logging, metrics, tracing, alerting, SLI/SLO coverage
  • optimization-audit — algorithm efficiency, database queries, caching, concurrency, cloud cost
  • cognitive-interface-audit — usability, mental model alignment, cognitive load, accessibility (if UI exists)
  • documentation-audit — linguistic precision, structural taxonomy, audience calibration, completeness

Read the full file on GitHub · 198 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. 1mo ago Changed · +1 lines 1a75437b4676
  2. 1mo ago Changed 094e37586907
  3. 2mo ago First seen · 197 lines · 80 tokens per session scan A 8ca8848716ef

Subscribe to this mod's changes

final-review is a skill published in the GitHub repository karsten-s-nielsen/mad-scientist-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 3,166 once invoked, about $0.0003 per session on Opus 5.5. 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.

Claude CodeCode reviewarchitecturec4-modelclaude-code-plugincode-qualityobservability
Related

final-review compared with skills from other repositories

final-review next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
final-reviewkarsten-s-nielsen/mad-scientist-skillsSkill31mo agoMITA80Claude Code
auditjlifyio/wyxSkill329d agoMITA81Claude Code
refactorzircote-plugins/refactorSkill25mo agoMITA112Claude Code
releasehyhmrright/brooks-lintSkill1.6kyesterdayMITA135Claude Code, Codex
recipe-front-reviewshinpr/claude-code-workflowsSkill7114d agoMITA29Claude Code
new-skillhyhmrright/brooks-lintSkill1.6kyesterdayMITA145Claude Code, Codex
brooks-audithyhmrright/brooks-lintSkill1.6kyesterdayMITA143Claude Code