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/danielgap/openclaw-planitor/data-crosschecknpx skills add danielgap/openclaw-planitor --skill data-crosscheckgit clone --depth 1 https://github.com/danielgap/openclaw-planitorWhat 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 | $0.00034 | $0.00641 |
| Opus 5 | $0.00017 | $0.00320 |
| Sonnet 5 | $0.00007 | $0.00128 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
data-crosscheck 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 2d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Data Cross-Check
Descripción
Verifica datos específicos del plan de negocio contra fuentes externas. Delega a investigación web para confirmar o refutar cada dato. Se ejecuta en Fase 7 (JUDGE).
Proceso
- Leer el plan de negocio (
plan-final.mdo artefactos JSON) - Extraer datos verificables (números, porcentajes, afirmaciones concretas)
- Para cada dato, delegar a investigación web: "Verifica este dato: X. Fuente original: plan de negocio."
- Generar
CROSS-CHECK-REPORT.jsoncon resultados
Formato de Salida
Archivo: projects/{proyecto}/v{n}/CROSS-CHECK-REPORT.json
{
"project": "{proyecto-id}",
"checked_at": "ISO date",
"checks": [
{
"claim": "TAM de 150.000 personas en Palencia",
"source_plan": "Sección 3.1",
"verified": "true|false|partial|unverifiable",
"actual_value": "148.000 (INE 2024)",
"confidence": "high|medium|low",
"notes": "..."
}
],
"summary": {
"total": 10,
"verified": 7,
"refuted": 1,
"partial": 2,
"unverifiable": 0
}
}
Cómo Delegar a investigación web
Usar delegar al modelo a investigación web:
Delega a investigación web:
"Verifica este dato: {claim}.
Fuente original: plan de negocio, sección {source}.
Busca fuentes independientes que confirmen o refuten el dato.
Responde con: verified (true/false/partial), actual_value, confidence, notes."
Schema
El report sigue el schema en schemas/cross-check-report.schema.json.
Reglas
- Solo verificar datos numéricos o hechos concretos (no opiniones ni proyecciones internas)
- Máximo 20 checks por ejecución
- Si un dato no se puede verificar, marcar como "unverifiable" (no "false")
- Priorizar checks en: TAM/SAM/SOM, precios de mercado, costes, datos demográficos
- Los datos de proyecciones internas (break-even, cash flow) NO se cross-checkean
- Si más del 30% de datos son refutados → flag como issue crítico para JUDGE
Integración con Pipeline
- Fase 7 (JUDGE): Ejecutar cross-check antes del judgment
- JUDGE debe incluir
CROSS-CHECK-REPORT.jsonen su evaluación - Si hay refutados → issue crítico, potencial vuelta a la fase origen
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.
- 2d ago First seen · 79 lines · 34 tokens per session scan A 17a3618bf88f
data-crosscheck is a skill published in the GitHub repository danielgap/openclaw-planitor (5 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 641 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.