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.
npx skills add chekusu/wanman --skill cross-validationgit clone --depth 1 https://github.com/chekusu/wanmanWrote 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/chekusu/wanman/cross-validation)<a href="https://agentmods.dev/skills/chekusu/wanman/cross-validation"><img src="https://agentmods.dev/badge/skills/chekusu/wanman/cross-validation/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.
<a href="https://agentmods.dev/skills/chekusu/wanman/cross-validation"><img src="https://agentmods.dev/badge/skills/chekusu/wanman/cross-validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00014 | $0.00782 |
| Opus 5.5 | $0.00006 | $0.00313 |
| Sonnet 5.5 | $0.00003 | $0.00156 |
| Haiku 4.5 | $0.00001 | $0.00078 |
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 1mo 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Output Consistency Validation
When to Execute
After wanman task list shows all tasks with status=done, perform output consistency validation before inspecting artifact data.
Validation Process
Step 1: Collect All Output Files
# List all agent output files
find /workspace/agents -name "*.md" -o -name "*.html" | grep -v CLAUDE.md | sort
Step 2: Extract Key Facts
Extract the following key information from each file:
| Fact Type | Example |
|---|---|
| Brand name | "COFFEE TO" |
| Tagline | "Coffee to, begin." |
| Address | 2-XX-XX Kamimeguro, Meguro-ku, Tokyo |
| Business hours | 8:00 - 20:00 |
| Opening date | 2026.4.1 |
| Menu prices | Drip Coffee ¥500 |
| Instagram handle | @coffee.to.nakameguro |
| Color HEX values | #2D1B0E, #F5E6D3 |
Step 3: Compare for Consistency
Cross-check file by file:
Brand guide (marketing) brand name ←→ Website (dev) brand name
Brand guide tagline ←→ Poster (marketing) tagline
Brand guide colors ←→ Website CSS colors
Financial report pricing ←→ Website menu prices
Poster opening date ←→ Social media content date
Poster address ←→ Website address
Step 4: Handle Inconsistencies
When inconsistencies are found, defer to the earliest completed authoritative document (usually the brand guide) and create a correction task:
# Example: website brand name does not match brand guide
wanman task create "Fix website brand name: unify the brand name on the website from 'KAWA' to 'COFFEE TO' as specified in the brand guide. Update all brand names, taglines, and Instagram handles in index.html. Reference: /workspace/agents/output/marketing/brand-design.md" --assign dev --priority 1
Authoritative Document Priority
When information conflicts, follow this order of precedence:
- Brand guide — Brand name, tagline, visual style
- Financial report — Prices, cost data
- Market research — Competitor data, market data
- Website/posters — Must align with the above (not a source of truth)
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.
- 1mo ago First seen · 89 lines · 14 tokens per session scan A 0de1858dfd0a
cross-validation is a skill published in the GitHub repository chekusu/wanman (694 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 14 tokens to every session and 782 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
github
GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…
hypotheses
Turns a research direction into testable hypotheses with predictions, competing explanations and the experiments that discriminate between them, including the design (controls, randomization, blocking), sample size or seed count, the pre-specified analysis, and the result that would falsify each hypothesis. Use when a…
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.
control-center-review
Review one captured Control Center build before runtime activation.
review-pr
Review GitHub pull requests. Use when user says "review PR", "review pull request", or "/review-pr".