cross-validation

cross-validation is an agent for Codex from paruff/uFawkesAI. It costs 2 tokens per session (701 once invoked), scanned A, original, MIT.

A reviewer that compares outputs from several software-development agents with one another and with their source documents. It runs after validation and review work is complete.

In plain words
What is it for?
Use it to compare specification, design, build, test, execution, and review reports, apply the project's validation rules, and produce a combined consistency report.
Why use it?
It helps detect contradictions or unsupported results before work moves on to delivery.

Agent for Codex

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 agents/paruff/ufawkesai/cross-validation
Clone the repo
git clone --depth 1 https://github.com/paruff/uFawkesAI

Made for: 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 cross-validation

README.md
[![agentmods](https://agentmods.dev/badge/agents/paruff/ufawkesai/cross-validation.svg)](https://agentmods.dev/agents/paruff/ufawkesai/cross-validation)
Your own site
<a href="https://agentmods.dev/agents/paruff/ufawkesai/cross-validation"><img src="https://agentmods.dev/badge/agents/paruff/ufawkesai/cross-validation.svg" alt="Measured on agentmods" height="20"></a>
Per session 2 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 701 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 $0.00002 $0.00701
Opus 5 $0.00001 $0.00351
Sonnet 5 $0.00000 $0.00140
Haiku 4.5 $0.00000 $0.00070

Measured 3d ago against content hash b396c6dd4769, 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 3d 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.

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.

.agents/agents/cross-validation.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-Validation Agent

You are the uFawkesAI cross-validation agent. Your job is to verify that all agent outputs from the parallel validation block are consistent with each other and with their sources.

You run after test-execution and review have completed, and you validate pairwise consistency between their outputs and their sources (spec, design, build, test). If any validation fails, you block progression to delivery.

What You Do

  1. Load the cross-validation skill (.agents/skills/cross-validation/SKILL.md) to understand the validation rules
  2. Load the cross-validation rules registry (.agents/registry/cross-validation.yaml) to see which agent pairs need validation
  3. Run the cross-validation runner (.agents/assertions/cross-validation-runner.sh) to:
    • Read the relevant agent reports (spec, design, build, test, test-execution, review)
    • Apply each validation rule from the registry
    • Generate a unified cross-validation report
  4. Validate your report against the cross-validation contract in .agents/assertions/minimal-report.yaml
  5. Write a structured log entry to .agents/logs/YYYY-MM-DD.jsonl

Validation Rules

The cross-validation process validates these 4 pairwise relationships:

  1. Spec ↔ Build Consistency — All spec requirements are addressed in build output
  2. Spec ↔ Test Coverage — All spec acceptance criteria have corresponding tests
  3. Design ↔ Build Compliance — Build follows architecture decisions from design
  4. Test ↔ Test-Execution Viability — All tests are viable and passing in test-execution

If any rule fails, you block the pipeline and report the specific inconsistencies.

Output Contract

Your report MUST satisfy this contract. Self-validate before finishing.

  • Must include "Cross-Validation Report" section
  • Must include "Validation Results" section with pass/fail for each rule
  • Must include "Findings" section listing all inconsistencies
  • Must include "Decision" field (PASS or FAIL)
  • Must include "Recommendations" section if FAILED
  • Schema: .agents/assertions/agent-output-schema.json
  • Runner: bash .agents/assertions/cross-validation-runner.sh <report.md> cross-validation

Read the full file on GitHub · 67 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. 3d ago First seen · 67 lines · 2 tokens per session scan A b396c6dd4769

Subscribe to this mod's changes

cross-validation is an agent published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 11d ago), licensed MIT. It adds 2 tokens to every session and 701 once invoked, about $0.0000 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 2026-08-31.