gold-review

gold-review is a skill for Claude Code, Codex from NVIDIA-NeMo/Switchyard. It costs 74 tokens per session (2,029 once invoked), scanned A, original, Apache-2.0.

A review workflow for checking whether a CRAFT Search benchmark task's official answer is supported by the source code. CRAFT Search is a benchmark for evaluating answers to code-search questions.

In plain words
What is it for?
Use it to inspect a task's gold files, assertions, explanations, and available agent runs, then produce specific recommendations.
Why use it?
It helps find incorrect functions, claims, tests, or explanations instead of accepting an answer merely because several agents agreed with it.

Skill for Claude CodeCodex

About the project

Switchyard is a model-routing library and proxy that chooses which language model should handle each LLM request, based on factors such as cost and task suitability. It is for developers running LLM applications who want to route calls through existing gateways, custom harnesses, or a standalone proxy while retaining OpenAI and Anthropic client compatibility. The catalogue add-ons are workflows for operating or integrating Switchyard with coding agents and gateways.

NVIDIA-NeMo/Switchyard · 2,713 stars · on GitHub

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/nvidia-nemo/switchyard/gold-review
Any agent
npx skills add NVIDIA-NeMo/Switchyard --skill gold-review
Clone the repo
git clone --depth 1 https://github.com/NVIDIA-NeMo/Switchyard

Made for: Claude Code, Codex.

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 gold-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia-nemo/switchyard/gold-review.svg)](https://agentmods.dev/skills/nvidia-nemo/switchyard/gold-review)
Your own site
<a href="https://agentmods.dev/skills/nvidia-nemo/switchyard/gold-review"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/switchyard/gold-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,029 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 5.1 $0.00074 $0.02029
Opus 5 $0.00037 $0.01014
Sonnet 5 $0.00015 $0.00406
Haiku 4.5 $0.00007 $0.00203

Measured 6d ago against content hash a58a34abf874, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

gold-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 6d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/apply_annotations.py, scripts/load_task.py, scripts/read_gold_functions.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

experimental/craft-taskgen/src/craft_taskgen/search/templates/gold-review/skills/gold-review/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRAFT Search Gold Data Review

Systematic evaluation of gold answer quality for CRAFT Search benchmark tasks.

Trigger

User mentions a task ID like craft-httpx-9e2db24f or asks to review/investigate a specific task's gold data.

Critical Principle

Do NOT trust agent consensus. The agents are the subjects being measured — using their majority vote to validate the gold answer is circular reasoning. Agent output is a secondary signal at best. The primary evidence is YOUR OWN deep reading of the source code. If 7/7 agents report a function but the code shows it's irrelevant to the question, it stays out. If 0/7 agents report a function but the code shows it's the core mechanism, it goes in.

Workflow

1. Load task data

Run the loader script, which prints instruction, gold answer, tiers, and consensus counts:

uv run python .claude/skills/gold-review/scripts/load_task.py <task-id>

Read the output. Understand the question being asked — this anchors everything.

1.5. Trajectory Integrity Check

Run trajectory-based integrity checks against agent runs (if job dirs are available):

uv run python .claude/skills/gold-review/scripts/trajectory_integrity_check.py <task-id> \
    --job-dirs <opus-job-dir> <codex-job-dir>

This checks for four issues (from the agentic-benchmark-eval checklists):

Check What it detects Action if FAIL
Gold Contamination Agent read /tests/gold_answer.json or /solution/solve.sh Task is invalid — recommend reject
Memorization High reward (>0.5) with <3 tool calls Gold may be too easy or leaked — investigate
Exploration Coverage Agent claims files in answer.json that it never actually read Agent may have hallucinated files — check gold scope
Answer Leakage Instruction text contains gold file paths or private function names Instruction needs adversarial rewrite

If no job dirs are available, skip this step — the checks require agent trajectory data.

Read the full file on GitHub · 171 lines

Files

What ships with it

7 files 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. 6d ago First seen · 171 lines · 74 tokens per session scan A a58a34abf874

Subscribe to this mod's changes

gold-review is a skill published in the GitHub repository NVIDIA-NeMo/Switchyard (2,713 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 2,029 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens