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 danielgap/openclaw-planitor --skill dual-llm-reviewgit clone --depth 1 https://github.com/danielgap/openclaw-planitorWrote 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/danielgap/openclaw-planitor/dual-llm-review)<a href="https://agentmods.dev/skills/danielgap/openclaw-planitor/dual-llm-review"><img src="https://agentmods.dev/badge/skills/danielgap/openclaw-planitor/dual-llm-review/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/danielgap/openclaw-planitor/dual-llm-review"><img src="https://agentmods.dev/badge/skills/danielgap/openclaw-planitor/dual-llm-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00976 |
| Opus 5 | $0.00000 | $0.00488 |
| Sonnet 5 | $0.00000 | $0.00195 |
| Haiku 4.5 | $0.00000 | $0.00098 |
Grade A, and why
dual-llm-review 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 10d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dual-LLM Review Skill
Propósito
Evaluación adversarial usando dos modelos LLM diferentes en paralelo para fases críticas del pipeline. Reemplaza la dependencia en Modelo A y Modelo B como agentes externos.
Filosofía
Un solo modelo tiene sesgos ciegos. Dos modelos independientes, con la misma información, generan perspectivas complementarias que se fusionan en una evaluación más robusta.
Configuración
Modelos requeridos
| Rol | Modelo | Propósito |
|---|---|---|
| Reviewer A | Modelo principal del agente | Evaluación desde perspectiva analítica |
| Reviewer B | Modelo secundario (diferente provider) | Evaluación desde perspectiva alternativa |
Regla: Los dos modelos deben ser de providers diferentes (ej: GLM + GPT, Claude + Gemini).
Si solo hay un modelo disponible
- Usar el mismo modelo con dos prompts diferentes (perspectiva optimista vs pesimista)
- Advertir en el reporte que no hubo dual-LLM real
Fases Dual-LLM
Fase 5: Strategy
- Reviewer A: DAFO desde perspectiva interna (fortalezas/debilidades)
- Reviewer B: DAFO desde perspectiva externa (oportunidades/amenazas)
- Fusión: DAFO completo + estrategia de posicionamiento
Fase 6: Build
- Reviewer A: Redacción del plan con enfoque conservador
- Reviewer B: Redacción del plan con enfoque ambicioso
- Fusión: Plan equilibrado con rango de escenarios
Fase 8: Judge
- Reviewer A: Evaluación técnica (datos, cálculos, coherencia)
- Reviewer B: Evaluación estratégica (viabilidad, timing, riesgos)
- Fusión: JUDGE-REPORT con score único y veredicto
Protocolo de Ejecución
1. Preparar input idéntico para ambos reviewers
2. Ejecutar Reviewer A → output_a
3. Ejecutar Reviewer B → output_b
4. Comparar outputs:
a. Puntos de acuerdo → Alta confianza
b. Puntos de desacuerdo → Flag para revisión manual
c. Puntos únicos de cada reviewer → Incorporar si aportan valor
5. Generar output fusionado
6. Documentar discrepancias en sección "Dual-LLM Notes"
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.
- 10d ago First seen · 113 lines · 0 tokens per session scan A 27e5153899b5
dual-llm-review is a skill published in the GitHub repository danielgap/openclaw-planitor (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 976 tokens. 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…