Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/paruff/uFawkesAInpx agentmods add skills/paruff/ufawkesai/cross-validationWrote 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.
[](https://agentmods.dev/skills/paruff/ufawkesai/cross-validation)<a href="https://agentmods.dev/skills/paruff/ufawkesai/cross-validation"><img src="https://agentmods.dev/badge/skills/paruff/ufawkesai/cross-validation.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00002 | $0.01004 |
| Opus 5 | $0.00001 | $0.00502 |
| Sonnet 5 | $0.00000 | $0.00201 |
| Haiku 4.5 | $0.00000 | $0.00100 |
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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Validation Skill
The cross-validation skill enables the cross-validation agent to validate consistency between agent outputs and their sources. It provides the rules registry and validation runner that check pairwise consistency across the agent pipeline.
Skill Purpose
This skill implements cross-validation of the uFawkesAI agent pipeline. It validates that:
- Spec ↔ Build Consistency — All spec requirements are addressed in build output
- Spec ↔ Test Coverage — All spec acceptance criteria have corresponding tests
- Design ↔ Build Compliance — Build follows architecture decisions from design
- Test ↔ Test-Execution Viability — All tests are viable and passing in test-execution
Note: The review agent now consolidates review, build-review, and security capabilities. Review findings are validated as part of the build process.
How to Load
Load this skill when you need to validate cross-agent consistency:
Load `.agents/skills/cross-validation/SKILL.md`
Validation Rules Registry
The skill uses .agents/registry/cross-validation.yaml as the rules registry. This file defines:
- Which agent pairs need validation
- What specific consistency checks to perform
- How to extract and compare information from agent reports
Validation Runner
The skill provides .agents/assertions/cross-validation-runner.sh which:
- Reads the cross-validation rules from the registry
- Extracts relevant sections from agent reports (spec, design, build, test, test-execution, review)
- Applies each validation rule
- Generates a unified cross-validation report
- Returns PASS if all rules pass, FAIL otherwise
Usage Examples
Loading the Skill
Load `.agents/skills/cross-validation/SKILL.md`
Running Validation
bash .agents/assertions/cross-validation-runner.sh \
--spec-report path/to/spec-report.md \
--design-report path/to/design-report.md \
--build-report path/to/build-report.md \
--test-report path/to/test-report.md \
--test-execution-report path/to/test-execution-report.md \
--review-report path/to/review-report.md
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.
- 7d ago First seen · 143 lines · 2 tokens per session scan A 51645d498496
cross-validation is a skill published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 15d ago), licensed MIT. It adds 2 tokens to every session and 1,004 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.
Other skills, from other repositories
template-formal
Strongly-typed multiagent ant-robot colony exemplar — ADTs, session-typed protocols, affine-discipline resource handles, storage-as-functor framing, Active-Inference-flavored decision loop, mypy-as-oracle negative controls.
template-reproducibility-audit
Deterministic reproducibility audit — fixed seeds, regenerate-from-clean, double-run diff before Zenodo/arXiv/release. USE WHEN outputs drift between runs, "worked on my machine", need regenerate-from-clean proof, or pre-release reproducibility check — even without naming docs/prompts.
template-test-creation
Create pytest suites under the no-mocks policy — real data, temp files, subprocess, pytest-httpserver. USE WHEN adding tests, raising coverage, testing new src/ module, or user forbids mocks.
infrastructure-benchmark
Deterministic benchmark harnesses for public template exemplars. Use when scoring generated project outputs against benchmark manifests, refreshing the default template smoke manifest, checking publication-readiness rubrics, or adding bounded no-network readiness checks for public template outputs.
infrastructure-sia
Skill for the Self-Improvement Agent (SIA) harness contract. Use when validating task public/private layouts, generation artifact trees, evaluation runners, fixture replay loops, or opt-in live Meta→Target→Feedback cycles in template projects.
template-sia
SIA (Self-Improvement Agent) harness exemplar — Meta/Target/Feedback loops, public/private splits, fixture replay, fail-closed validation.