arn-code-review-implementation

A post-implementation quality check for comparing finished code with its project plan and documented coding, testing, and architecture patterns. It reports errors, warnings, and informational findings with a final verdict.

In plain words
What is it for?
Use it after executing a plan, especially for multi-phase work or features spanning several modules, to review the implementation.
Why use it?
It provides a final check for deviations or quality problems before the project is considered complete.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/appsvortex/arness/arn-code-review-implementation
Any agent
npx skills add AppsVortex/arness --skill arn-code-review-implementation
Clone the repo
git clone --depth 1 https://github.com/AppsVortex/arness

Made for: Claude Code, Codex.

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,389 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00105 $0.03389
Opus 5 $0.00053 $0.01695
Sonnet 5 $0.00021 $0.00678
Haiku 4.5 $0.00011 $0.00339

Measured 2d ago against content hash 94cc32120d0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arn-code-review-implementation 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 2d 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/arn-code/skills/arn-code-review-implementation/SKILL.md · 286 lines

How it starts

The opening of the file, as written. The whole thing — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Arness Review Implementation

Post-execution quality gate that verifies an implementation matches the project plan and follows the stored code patterns, testing patterns, and architecture documentation. Reports issues classified as ERRORS, WARNINGS, and INFO, with a final verdict.

Pipeline position:

arn-code-init -> arn-code-feature-spec / arn-code-bug-spec -> arn-code-plan -> arn-code-save-plan -> arn-code-review-plan -> arn-code-taskify -> arn-code-execute-plan -> **arn-code-review-implementation**

This is a self-contained review -- it does not invoke sub-agents. The review is a structured, checklist-driven process: read code, compare to patterns, classify findings.

When to Use:

  • After arn-code-execute-plan completes
  • To verify that implementation matches the plan and follows stored patterns
  • Before considering the project done
  • Optional -- skip for small/straightforward projects; recommended for 3+ phases, multiple modules, or critical features

Prerequisites

If no ## Arness section exists in the project's CLAUDE.md, inform the user: "Arness is not configured for this project yet. Run /arn-implementing to get started — it will set everything up automatically." Do not proceed without it.

Workflow

Step 1: Load the Project

  1. Read the project's CLAUDE.md and extract the ## Arness section to find:
    • Plans directory path
    • Code patterns directory path
  2. Ask for PROJECT_NAME if not provided in the trigger message
  3. Read all project artifacts:
    • <project-folder>/INTRODUCTION.md -- codebase patterns that should have been followed
    • All reports in <project-folder>/reports/ -- what was implemented, tested, bugs fixed
    • All phase plans in <project-folder>/plans/ -- acceptance criteria, expected files, expected patterns
  4. Read stored pattern documentation:
    • <code-patterns-dir>/code-patterns.md
    • <code-patterns-dir>/architecture.md
    • <code-patterns-dir>/testing-patterns.md
    • <code-patterns-dir>/ui-patterns.md (if it exists)
    • <code-patterns-dir>/security-patterns.md (if it exists)
  5. Build a review checklist from these sources: files that should exist, patterns that should have been applied, features that were planned, tests that should pass

Read the full file on GitHub · 286 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 286 lines · 105 tokens per session scan A 94cc32120d0a

Subscribe to this mod's changes

arn-code-review-implementation is a skill published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), licensed MIT. It adds 105 tokens to every session and 3,389 once invoked, about $0.0005 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 2026-08-30.