code-review

A broad code-review process for changes in a Plan Forge project, combining automated checks with human-style review.

In plain words
What is it for?
It helps inspect changed files, analyse the current plan, check security and testing, detect scope drift, compare Bash and PowerShell versions, and optionally gather reviews from multiple models.
Why use it?
It finds mechanical problems first so the review can focus on architecture, security, tests, scope, and project-specific rules before a merge.

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/srnichols/plan-forge/code-review
Any agent
npx skills add srnichols/plan-forge --skill code-review
Clone the repo
git clone --depth 1 https://github.com/srnichols/plan-forge

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00070 $0.02842
Opus 5 $0.00035 $0.01421
Sonnet 5 $0.00014 $0.00568
Haiku 4.5 $0.00007 $0.00284

Measured 2d ago against content hash 3d800cf9a6c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Plan-Forge-specific: dual-shell parity (every PowerShell entry point has a matching Bash one), no sync `child_process` in the orchestrator hot path, `path.join(...)` everywhere (no hardcoded `\` or `/`)
.github/skills/code-review/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Skill — Plan Forge

Run /clean-code-review FIRST. That skill is the mechanical/quantitative pass: 44 CHECKS across 11 languages (JS/TS, Python, .NET, Java/Kotlin, Go, Rust, PHP, Swift, Ruby, PowerShell, Bicep) — module size, function complexity, parameter counts, duplication (jscpd + literal/regex scanners), engineering hygiene (empty catches, magic numbers, dead imports, TODO/FIXME, hardcoded secrets, SQL-injection, command-injection patterns), shell-parity (PS/Bash twins), enums-drift (pforge-mcp/enums.mjs), cross-package dependency boundaries, and ESLint. This skill is the qualitative/judgment pass. Mechanical findings clear the noise so this review can focus on what actually requires judgment.

Trigger

"Review my code" / "Run code review" / "Check before merge" / "Code review --quorum"

Steps

0. Forge Analysis

Use the forge_analyze MCP tool with the current plan (if available) to get a structured consistency score. Use the forge_diff MCP tool to detect scope drift and forbidden file edits.

If --quorum was specified: Use forge_analyze with quorum: true to dispatch multi-model analysis. Each changed file is independently reviewed by multiple AI models, and findings are synthesized with consensus confidence levels.

1. Identify Changed Files

# What changed since the merge-base with planning/main?
git diff --name-only origin/planning/main...HEAD

# Or since last commit
git diff --name-only HEAD~1

2. Public Surface Diff (consumer impact)

node scripts/audit/surface-diff.mjs
node scripts/audit/surface-diff.mjs --base origin/master

Parse docs/plans/cleanup-findings/raw/surface-diff-report.json. Three layers are diffed against the merge-base:

Layer Source What's compared
Module exports every .mjs outside tests/ added/removed named exports
MCP tools pforge-mcp/server.mjs TOOLS array added/removed tool names + inputSchema property keys
CLI commands pforge.ps1, pforge.sh added/removed top-level dispatch branches

Read the full file on GitHub · 184 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. 2d ago First seen · 184 lines · 70 tokens per session scan A 3d800cf9a6c3

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 22d ago), licensed MIT. It adds 70 tokens to every session and 2,842 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

aspire

Build, upgrade, and operate Aspire 13.5.x C# or TypeScript application hosts with the current CLI, AppHost, ServiceDefaults, integrations, dashboard, testing, MCP, and deployment patterns for distributed apps. USE FOR: Aspire.AppHost.Sdk, Aspire.Hosting., DistributedApplication.CreateBuilder, apphost.mts…

managedcode/dotnet-skills · 145 tokens

microsoft-agent-framework

Build .NET AI agents, harnesses, and multi-agent workflows with Microsoft Agent Framework using the right agent type, sessions, tools, workflows, hosting protocols, and enterprise guardrails. USE FOR: building or reviewing .NET code that uses Microsoft.Agents., Microsoft.Extensions.AI, AIAgent, HarnessAgent…

managedcode/dotnet-skills · 138 tokens

signalr

Implement or review SignalR hubs, streaming, reconnection, transport, and real-time delivery patterns in ASP.NET Core applications. USE FOR: building chat, notification, collaboration, or live-update features; debugging hub lifetime, connection state, or transport issues; deciding whether SignalR or another. DO NOT…

managedcode/dotnet-skills · 109 tokens

wpf

Build and modernize WPF applications on .NET with correct XAML, data binding, commands, threading, styling, and Windows desktop migration decisions. USE FOR: working on WPF UI, MVVM, binding, commands, or desktop modernization; migrating WPF from .NET Framework to .NET; integrating newer Windows capabilities into a…

managedcode/dotnet-skills · 122 tokens

worker-services

Build long-running .NET background services with BackgroundService, Generic Host, graceful shutdown, configuration, logging, and deployment patterns suited to workers and daemons. USE FOR: background services; scheduled workers; hosted services; worker extraction; graceful shutdown, health checks, and service hosting…

managedcode/dotnet-skills · 109 tokens

azure-functions

Build, review, or migrate Azure Functions in .NET with correct execution model, isolated worker setup, bindings, DI, and Durable Functions patterns. USE FOR: working on Azure Functions in .NET; migrating from the in-process model to the isolated worker model; adding Durable Functions, bindings, or host configuration.…

managedcode/dotnet-skills · 113 tokens