cross-validation

cross-validation is a skill for Claude Code, Codex from aneja5/forge-skills. It costs 57 tokens per session (1,365 once invoked), scanned A, original, MIT.

A two-stage process for getting independent reviews of an important design or product decision and turning the responses into agreed actions.

In plain words
What is it for?
Use it to prepare review questions, collect feedback from multiple reviewers, identify consensus, and turn findings into concrete changes.
Why use it?
It exposes blind spots before a costly decision is finalized. A self-contained review prompt and a structured response summary make feedback easier to compare and apply.

Skill for Claude CodeCodex

Part of the forge-skills plugin — 42 skills, 36 commands, 13 agents, 1 hook shipped together

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/aneja5/forge-skills/cross-validation
Any agent
npx skills add aneja5/forge-skills --skill cross-validation
Clone the repo
git clone --depth 1 https://github.com/aneja5/forge-skills

Made for: Claude Code, Codex.

Or install forge-skills, the plugin that ships this one along with the rest of its 42 skills, 36 commands, 13 agents, 1 hook.

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 cross-validation

README.md
[![agentmods](https://agentmods.dev/badge/skills/aneja5/forge-skills/cross-validation.svg)](https://agentmods.dev/skills/aneja5/forge-skills/cross-validation)
Your own site
<a href="https://agentmods.dev/skills/aneja5/forge-skills/cross-validation"><img src="https://agentmods.dev/badge/skills/aneja5/forge-skills/cross-validation.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,365 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 $0.00057 $0.01365
Opus 5 $0.00028 $0.00682
Sonnet 5 $0.00011 $0.00273
Haiku 4.5 $0.00006 $0.00136

Measured yesterday against content hash 049d0509f892, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cross-validation 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.

skills/cross-validation/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Validation

Overview

Two-phase skill with a human step in the middle. Phase 1: compile a self-contained prompt that any reviewer can assess without prior context. Phase 2: synthesize responses into consensus levels and actionable changes. The prompt must stand alone — a reviewer should need zero prior context.

When to Use

  • Major architectural or product decisions need external validation
  • User wants to check blind spots before committing to a direction
  • Multiple reviewers (human or AI) will assess the same document
  • High-stakes decisions where being wrong is expensive

When NOT to Use

  • Quick sanity check on a small decision — just ask directly
  • Code review — use code-review-and-quality
  • No .forge/prd.md or .forge/architecture.md exists yet — produce artifacts first

Common Rationalizations

Thought Reality
"We've already thought about this enough" Internal teams develop blind spots. External eyes catch what you've normalized
"The prompt doesn't need full context" If a reviewer has to ask clarifying questions, the prompt failed
"Three reviewers said it's fine, so it's fine" Unanimous approval is less valuable than one specific objection
"Disagreements mean someone is wrong" Disagreements reveal hidden assumptions — both sides may be partially right
"We can synthesize informally" Informal synthesis loses minority opinions. Structured synthesis surfaces them

Red Flags

  • Prompt requires prior context to understand (not self-contained)
  • Questions are generic ("is this good?") instead of specific ("does the auth model handle session revocation within 5 seconds?")
  • Synthesis ignores dissenting opinions
  • All reviewers agree on everything (questions were too soft)
  • Synthesis doesn't distinguish consensus levels

Core Process — Phase 1: Generate Prompt

Re-entry check: If .forge/cross-validation-prompt.md already exists and the user provides reviewer responses, skip to Phase 2.

Read the full file on GitHub · 118 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 · 118 lines · 57 tokens per session scan A 049d0509f892

Subscribe to this mod's changes

cross-validation is a skill published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 1,365 once invoked, about $0.0003 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 2026-09-03.