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 agentmods add skills/aneja5/forge-skills/cross-validationnpx skills add aneja5/forge-skills --skill cross-validationgit clone --depth 1 https://github.com/aneja5/forge-skillsWrote 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/aneja5/forge-skills/cross-validation)<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>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 | $0.00057 | $0.01365 |
| Opus 5 | $0.00028 | $0.00682 |
| Sonnet 5 | $0.00011 | $0.00273 |
| Haiku 4.5 | $0.00006 | $0.00136 |
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.
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.mdor.forge/architecture.mdexists 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.
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.
- yesterday First seen · 118 lines · 57 tokens per session scan A 049d0509f892
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.
Other skills, from other repositories
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
implement
Use when implementing a spec or GitHub ticket in this checkout.
loop-on-ci
Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
run-smoke-tests
Run Playwright smoke tests, debug failures, and verify fixes. Use for smoke, e2e, Playwright, or pre-ship browser verification.
browser-use
Drive a real browser to QA a running app. Screenshots, clicks, forms, evidence. Use when there is no Playwright suite, or when a human flow must be walked.
tdd
Use when implementing features or bug fixes test-first.