technical-accuracy-judge

technical-accuracy-judge is an agent for Claude Code from closedloop-ai/claude-plugins. It costs 25 tokens per session (3,763 once invoked), scanned A, original, Apache-2.0.

A technical fact checker for AI assistant answers about APIs, programming-language features, algorithms, and related concepts. It returns scored evaluations based on factual correctness.

In plain words
What is it for?
Use it to review generated code and technical explanations for correct API calls, language details, algorithms, and terminology.
Why use it?
It helps catch nonexistent APIs, incorrect method signatures, invalid usage, and technically unsound explanations before they are used in code or documentation.

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 review generated code and technical explanations for correct API calls, language details, algorithms, and terminology.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/closedloop-ai/claude-plugins/technical-accuracy-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 technical-accuracy-judge

README.md
[![agentmods](https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/technical-accuracy-judge/github.svg)](https://agentmods.dev/agents/closedloop-ai/claude-plugins/technical-accuracy-judge)
Your own site
<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/technical-accuracy-judge"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/technical-accuracy-judge/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 technical-accuracy-judge

Your own site · 80×15
<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/technical-accuracy-judge"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/technical-accuracy-judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,763 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00025 $0.03763
Opus 5 $0.00013 $0.01881
Sonnet 5 $0.00005 $0.00753
Haiku 4.5 $0.00003 $0.00376

Measured yesterday against content hash 51359f7c7634, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

technical-accuracy-judge 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- ✅ EXCELLENT: `requests.get(url, headers={'Authorization': 'Bearer token'})` - correct API usage
plugins/judges/agents/technical-accuracy-judge.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Accuracy Judge

Your Role and Expertise

You are an expert technical reviewer with deep knowledge across multiple programming languages, frameworks, APIs, algorithms, and computer science fundamentals. Your task is to rigorously evaluate the technical accuracy of AI assistant responses.

You must assess whether code, API usage, algorithmic explanations, and technical terminology are factually correct and technically sound. You are not judging style, completeness, or helpfulness—only technical correctness.

Evaluation Criteria

Assess the response across four technical accuracy dimensions. For each dimension, you must assign a score of 1.0 (EXCELLENT), 0.5 (FAIR), or 0.0 (FAILING) based on the criteria below:

1. API_CORRECTNESS

Threshold: 0.8 | Score: 1.0 (EXCELLENT), 0.5 (FAIR), or 0.0 (FAILING)

Evaluate whether API calls, method signatures, and library usage are factually correct and match real APIs.

EXCELLENT (1.0) - Assign when ALL of the following are true:

  • All function/method names exist and are spelled correctly
  • All parameter names match the actual API signature
  • Parameter types and ordering are correct
  • Import statements and module paths are accurate
  • No deprecated, removed, or non-existent APIs are referenced
  • API behavior descriptions match actual documentation
  • Special case: If no APIs are mentioned or APIs are not applicable to the topic, score as EXCELLENT

FAIR (0.5) - Assign when:

  • Most API usage is correct with only 1-2 minor parameter naming issues that don't affect functionality
  • Slightly outdated but still valid/supported API usage (e.g., older but not deprecated syntax)
  • Core API structure and behavior are correct despite minor imperfections

FAILING (0.0) - Assign when ANY of the following are true:

  • Wrong function/method names or multiple misspellings
  • Incorrect method signatures or parameter structures
  • Invalid parameter names or types that would cause errors
  • Incorrect import paths that would fail
  • Reference to deprecated, removed, or fictional APIs
  • Fundamental misunderstanding of how the API works

Read the full file on GitHub · 345 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 · 345 lines · 25 tokens per session scan A 51359f7c7634

Subscribe to this mod's changes

technical-accuracy-judge is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 2d ago), licensed Apache-2.0. It adds 25 tokens to every session and 3,763 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

csharp-reviewer

Expert C# code reviewer specializing in .NET conventions, async patterns, security, nullable reference types, and performance. Use for all C# code changes. MUST BE USED for C# projects.

affaan-m/ECC · 44 tokens

php-reviewer

Expert PHP code reviewer specializing in PSR-12 compliance, PHP type system, Eloquent ORM patterns, security, and performance. Use for all PHP code changes. MUST BE USED for PHP projects.

affaan-m/ECC · 44 tokens

python-reviewer

A Python code-review role focused on readability, standard Python style, type annotations, security, error handling, and performance.

xu-xiang/everything-claude-code-zh · 63 tokens

go-reviewer

A specialist reviewer for Go code, the programming language created at Google. It checks changed Go files for security, error handling, concurrent code, performance, and common Go style problems.

xu-xiang/everything-claude-code-zh · 54 tokens

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

vue-reviewer

Expert Vue.js code reviewer specializing in Composition API correctness, reactivity pitfalls, component architecture, template security, and Vue-specific performance. Use for any change touching .vue, .ts/.js files with Vue imports, or Vue ecosystem code (Pinia, Vue Router, Nuxt). MUST BE USED for Vue projects.

affaan-m/ECC · 68 tokens