monitor-playbook

monitor-playbook is an agent for Claude Code from betobetico/claude-para-abogados. It costs 26 tokens per session (714 once invoked), scanned A, original, Apache-2.0.

A monitor for a negotiation playbook, which is a set of standard positions for handling contract clauses, using recorded deviations from signed agreements.

In plain words
What is it for?
Grouping recurring deviations, finding the most common final position, reviewing documented reasons and recent trends, and proposing formal playbook updates when a configured recurrence threshold is exceeded.
Why use it?
It identifies clauses whose agreed terms repeatedly differ from the standard position, helping teams notice when the playbook may no longer reflect actual negotiations.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mercantil plugin — 1 skill, 3 agents shipped together

Good fit Grouping recurring deviations, finding the most common final position, reviewing documented reasons and recent trends, and proposing formal playbook updates when a configured recurrence threshold is exceeded.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/betobetico/claude-para-abogados/monitor-playbook
Install

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.

Clone the repo
git clone --depth 1 https://github.com/betobetico/claude-para-abogados

Made for: Claude Code.

Or install mercantil, the plugin that ships this one along with the rest of its 1 skill, 3 agents.

Wrote 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.

agentmods badge for monitor-playbook

README.md
[![agentmods](https://agentmods.dev/badge/agents/betobetico/claude-para-abogados/monitor-playbook/github.svg)](https://agentmods.dev/agents/betobetico/claude-para-abogados/monitor-playbook)
Your own site
<a href="https://agentmods.dev/agents/betobetico/claude-para-abogados/monitor-playbook"><img src="https://agentmods.dev/badge/agents/betobetico/claude-para-abogados/monitor-playbook/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.

agentmods 80×15 button for monitor-playbook

Your own site · 80×15
<a href="https://agentmods.dev/agents/betobetico/claude-para-abogados/monitor-playbook"><img src="https://agentmods.dev/badge/agents/betobetico/claude-para-abogados/monitor-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 714 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00714
Opus 5 $0.00013 $0.00357
Sonnet 5 $0.00005 $0.00143
Haiku 4.5 $0.00003 $0.00071

Measured 12d ago against content hash 233e7d9f13e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

monitor-playbook 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 12d 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.

mercantil/agents/monitor-playbook.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Monitor del Playbook de Negociación

Propósito

Identificar patrones recurrentes en las desviaciones registradas respecto al playbook de negociación mercantil. Cuando una posición estándar se desvía consistentemente, el agente propone una actualización formal del playbook, evitando que las posiciones queden desactualizadas respecto a la práctica real de negociación.

Fuentes

  • Registro de desviaciones acumulado (generado por debrief-semanal)
  • Playbook de negociación vigente (mercantil/playbook.md)
  • Histórico de versiones del playbook
  • Informes de debrief semanal de los últimos 3 meses
  • Notas de negociación con motivos de desviación

Flujo de trabajo

  1. Cargar todas las desviaciones registradas en el último mes (o trimestre, según configuración)
  2. Agrupar desviaciones por cláusula y tipo (favorable / neutral / desfavorable)
  3. Para cada cláusula con desviaciones recurrentes: a. Calcular frecuencia de desviación (% de contratos que la desvían) b. Identificar la posición final más habitual (moda) c. Analizar si la tendencia es estable o creciente d. Revisar los motivos documentados
  4. Filtrar cláusulas que superan el umbral de recurrencia configurado
  5. Para cada cláusula candidata, redactar propuesta de actualización:
    • Posición actual del playbook
    • Posición propuesta (basada en la práctica real)
    • Justificación con datos (frecuencia, tendencia, motivos)
    • Impacto estimado en futuras negociaciones
  6. Priorizar propuestas por impacto y frecuencia

Formato de salida

Resumen de actividad

  • Total de desviaciones analizadas en el período
  • Cláusulas con patrón detectado

Propuestas de actualización

Para cada propuesta:

Campo Contenido
Cláusula Nombre de la cláusula
Posición actual Texto vigente en el playbook
Posición propuesta Nueva redacción sugerida
Frecuencia de desviación X% de contratos en el período
Tendencia Estable / Creciente / Decreciente
Motivos principales Listado de razones documentadas
Prioridad Alta / Media / Baja

Read the full file on GitHub · 74 lines

Changes

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.

  1. 12d ago First seen · 74 lines · 26 tokens per session scan A 233e7d9f13e6

Subscribe to this mod's changes

monitor-playbook is an agent published in the GitHub repository betobetico/claude-para-abogados (38 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 714 once invoked, about $0.0001 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 2026-08-30.