playbook-monitor

playbook-monitor is an agent for Claude Code from Buildwise-Studios/claude-for-hk-law. It costs 114 tokens per session (2,179 once invoked), scanned A, original, Apache-2.0.

An automated monitor for a legal playbook, the internal guide that sets preferred positions on recurring contract terms.

In plain words
What is it for?
It checks the deviation log after deal debriefs, identifies repeated changes to the same clause within a configurable time window, and proposes updates for an attorney to approve or reject.
Why use it?
It detects when attorneys repeatedly depart from the written guidance, helping reveal when the playbook no longer matches accepted practice.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the commercial-legal plugin — 9 skills, 3 agents shipped together

Good fit It checks the deviation log after deal debriefs, identifies repeated changes to the same clause within a configurable time window, and proposes updates for an attorney to approve or reject.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/buildwise-studios/claude-for-hk-law/playbook-monitor
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/Buildwise-Studios/claude-for-hk-law

Made for: Claude Code.

Or install commercial-legal, the plugin that ships this one along with the rest of its 9 skills, 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 playbook-monitor

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/buildwise-studios/claude-for-hk-law/playbook-monitor"><img src="https://agentmods.dev/badge/agents/buildwise-studios/claude-for-hk-law/playbook-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,179 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 $0.00114 $0.02179
Opus 5 $0.00057 $0.01090
Sonnet 5 $0.00023 $0.00436
Haiku 4.5 $0.00011 $0.00218

Measured 12d ago against content hash 58399e12b34b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

playbook-monitor 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.

commercial-legal/agents/playbook-monitor.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Playbook Monitor Agent

Purpose

The gap between the playbook attorneys write and the positions they actually accept grows silently — because nobody has time to reconcile them after every deal. This agent watches the deviation log, detects when a position is being overridden consistently, and proposes a specific update to ~/.claude/plugins/config/claude-for-hk-law/commercial-legal/CLAUDE.md. The attorney approves or rejects. The playbook stays alive.

When it runs

Data-triggered, not calendar-triggered. After every deal-debrief run, this agent checks whether any clause has crossed the proposal threshold. If yes, it writes proposals and notifies the attorney. If no threshold is crossed, it does nothing and logs the check silently.

Default threshold: 5 deviations on the same clause within the last 12 months (excluding deals flagged exclude_from_patterns: true).

Both values are configurable in ~/.claude/plugins/config/claude-for-hk-law/commercial-legal/CLAUDE.md under ## Playbook monitor settings:

pattern_threshold: 5        # deviations before a proposal is triggered
lookback_months: 12         # rolling window for pattern detection

If these fields are absent from ~/.claude/plugins/config/claude-for-hk-law/commercial-legal/CLAUDE.md, use the defaults above.

What it does

Step 1 — Read the practice profile and log

  1. Read ~/.claude/plugins/config/claude-for-hk-law/commercial-legal/CLAUDE.md in full. Extract:

    • All current playbook positions for each clause category
    • Playbook monitor settings (threshold and lookback window), or use defaults
    • Notification destination (Slack channel or email from House style section)
  2. Read ~/.claude/plugins/config/claude-for-hk-law/commercial-legal/deviation-log.yaml. Filter out:

    • Any entry where exclude_from_patterns: true
    • Any entry with date_signed outside the configured lookback window

Step 2 — Detect patterns

For each clause key present in the filtered log, count deviations. Group by:

  • Clause (e.g., limitation_of_liability)
  • Direction of deviation (e.g., "accepted higher cap", "accepted uncapped")
  • Basis (e.g., counterparty_leverage, commercial_priority)

Read the full file on GitHub · 191 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 · 191 lines · 114 tokens per session scan A 58399e12b34b

Subscribe to this mod's changes

playbook-monitor is an agent published in the GitHub repository Buildwise-Studios/claude-for-hk-law (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 114 tokens to every session and 2,179 once invoked, about $0.0006 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.

Related

Other agents, from other repositories

penalista

Specialista in diritto penale italiano. Delega quando la questione riguarda reati, pene, prescrizione, misure cautelari o riti alternativi.

capazme/mcp-legal-it · 38 tokens

compliance-auditor

Expert compliance auditor specializing in regulatory frameworks, data privacy laws, and security standards. Masters GDPR, HIPAA, PCI DSS, SOC 2, and ISO certifications with focus on automated compliance validation and continuous monitoring.

NickCrew/Claude-Cortex · 52 tokens

leave-tracker

Weekly agent that monitors open employee statutory leave with hard legal deadlines — statutory maternity, paternity, adoption, shared parental, and parental bereavement leave under ERA 1996 and the associated Regulations; long-term sickness with reasonable-adjustments obligations under EqA 2010 — and fires…

uk-agents/uk-legal-plugins · 130 tokens

ip-renewal-watcher

Scheduled agent that reads the IP portfolio register, computes what's due, and posts a ranked deadline report. Runs weekly by default. Posts to the channel named in /.claude/plugins/config/uk-legal-plugins/ip-legal-uk/CLAUDE.md → Renewal alerts. Trigger phrases: "what's renewing", "IP deadlines", "portfolio check"…

uk-agents/uk-legal-plugins · 91 tokens

launch-watcher

Monitors the launch tracker (Jira/Linear) for upcoming launches that likely need UK legal review, flags them before product counsel gets surprised. Runs daily. Trigger: "what launches are coming", "what should I know about", "launch radar", or on schedule.

uk-agents/uk-legal-plugins · 59 tokens

reg-change-monitor

Scheduled agent that checks UK regulatory feeds and posts a filtered digest. Runs per the cadence in /.claude/plugins/config/uk-legal-plugins/regulatory-legal-uk/CLAUDE.md. Filters by materiality threshold so the digest is signal, not noise. Trigger: "reg digest", "what's new from UK regulators", "regulatory update"…

uk-agents/uk-legal-plugins · 82 tokens