goal-alignment-judge

goal-alignment-judge is an agent for Claude Code from closedloop-ai/claude-plugins. It costs 24 tokens per session (5,831 once invoked), scanned A, original, Apache-2.0.

A review tool that checks whether an implementation plan supports the main goals in a PRD, or product requirements document. It looks beyond listed tasks to the user problem the product should solve.

In plain words
What is it for?
Use it to compare a plan with a PRD, identify missing links to user intent, and report evidence and severity for each alignment gap.
Why use it?
It helps find plans that satisfy individual requirements but miss the underlying business or user goal. It also separates serious gaps from minor omissions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the judges plugin — 3 skills, 22 agents shipped together

Good fit Use it to compare a plan with a PRD, identify missing links to user intent, and report evidence and severity for each alignment gap.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/closedloop-ai/claude-plugins/goal-alignment-judge
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.

Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins

Made for: Claude Code.

Or install judges, the plugin that ships this one along with the rest of its 3 skills, 22 agents.

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 goal-alignment-judge

README.md
[![agentmods](https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/goal-alignment-judge.svg)](https://agentmods.dev/agents/closedloop-ai/claude-plugins/goal-alignment-judge)
Your own site
<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/goal-alignment-judge"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/goal-alignment-judge.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,831 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 $0.00024 $0.05831
Opus 5 $0.00012 $0.02916
Sonnet 5 $0.00005 $0.01166
Haiku 4.5 $0.00002 $0.00583

Measured yesterday against content hash e36df005b1e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

goal-alignment-judge 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 yesterday.

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/judges/agents/goal-alignment-judge.md · 488 lines

How it starts

The opening of the file, as written. The whole thing — 488 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal Alignment Judge

  • Goal extraction: Reading between the lines of product requirements to identify the core user intent — the "why" behind the "what" in addition to PRD's explicit why statement
  • Strategic alignment: Assessing whether technical deliverables collectively achieve a business objective, not just check boxes
  • Gap analysis: Identifying blind spots where an implementation plan addresses surface-level requirements but misses the deeper user goal
  • Criticality assessment: Distinguishing between gaps that undermine the core goal vs. minor omissions that don't affect goal achievement

Your task is to analyze implementation plans and score them based on goal alignment with the PRD. You evaluate, NOT fix — you identify alignment gaps with specific evidence and severity assessments.

<analysis_instructions>

Structured Thinking Process

You MUST think through your analysis step-by-step in <thinking> tags before producing output. Follow this exact sequence:

Step 1: Deep Goal Extraction

Read the requirement evidence in the envelope source-of-truth artifacts carefully and step back from the surface-level requirements. Ask yourself:

  • What is the user fundamentally trying to accomplish? Not "build feature X" but "solve problem Y" or "enable capability Z."
  • What business or functional outcome does success look like? Think about the end state the user envisions.
  • Who benefits and how? Identify the target users/stakeholders and what changes for them when this is done.

Distill the PRD into:

  1. Primary goal: One sentence capturing the core business/functional objective
  2. Goal components: 3-7 concrete sub-goals or success criteria that, when collectively achieved, mean the primary goal is met
  3. Critical components: Which goal components are essential (without them, the primary goal fundamentally fails) vs. which are enhancing (nice-to-have that improve the solution but aren't blocking)

Read the full file on GitHub · 488 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. yesterday First seen · 488 lines · 24 tokens per session scan A e36df005b1e1

Subscribe to this mod's changes

goal-alignment-judge is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 24 tokens to every session and 5,831 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 2026-09-07.

Related

Other agents, from other repositories

flutter-reviewer

Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.

affaan-m/ECC · 50 tokens

harmonyos-app-resolver

HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.

affaan-m/ECC · 49 tokens

gan-planner

GAN Harness — Planner agent. Expands a one-line prompt into a full product specification with features, sprints, evaluation criteria, and design direction.

affaan-m/ECC · 34 tokens

network-troubleshooter

Diagnoses network connectivity, routing, DNS, interface, and policy symptoms with a read-only OSI-layer workflow and evidence-backed root cause summary.

affaan-m/ECC · 34 tokens

eco-scout

Read-only codebase sweep that returns conclusions and path:line citations only, never file contents. Use for broad "where is X / what touches Y" questions across many files, when reading them all in the main conversation would cost more than the answer is worth.

sup3x/claude-code-eco · 57 tokens

security-reviewer

Read-only, separate-context security reviewer. It reviews a changed diff for authentication / IAM / secrets / supply-chain / dependency risk and emits categorized findings (Block / Risk / Confirmed) for the operator to act on. Use it when an atom touches auth, identity/IAM, credentials or secrets, dependency…

lukasrepublic/agentic-foundry · 108 tokens