deal-debrief

deal-debrief is an agent for Claude Code from ZekaiSuni/claude-for-legal-turkish. It costs 29 tokens per session (669 once invoked), scanned A, original, Apache-2.0.

A weekly review agent for recently signed commercial agreements in Turkish. It compares each agreement with the team's legal playbook—a set of preferred contract positions—and records why any differences were accepted.

In plain words
What is it for?
Use it to review signed agreements, identify changes to limits on liability, penalties, data protection, intellectual property, renewals, and termination, then ask an attorney to explain and log each difference.
Why use it?
It prevents useful lessons from signed contracts being lost and helps the legal team spot repeated departures from its usual terms.

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 Use it to review signed agreements, identify changes to limits on liability, penalties, data protection, intellectual property, renewals, and termination, then ask an attorney to explain and log each difference.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/zekaisuni/claude-for-legal-turkish/deal-debrief
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/ZekaiSuni/claude-for-legal-turkish

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 deal-debrief

README.md
[![agentmods](https://agentmods.dev/badge/agents/zekaisuni/claude-for-legal-turkish/deal-debrief/github.svg)](https://agentmods.dev/agents/zekaisuni/claude-for-legal-turkish/deal-debrief)
Your own site
<a href="https://agentmods.dev/agents/zekaisuni/claude-for-legal-turkish/deal-debrief"><img src="https://agentmods.dev/badge/agents/zekaisuni/claude-for-legal-turkish/deal-debrief/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 deal-debrief

Your own site · 80×15
<a href="https://agentmods.dev/agents/zekaisuni/claude-for-legal-turkish/deal-debrief"><img src="https://agentmods.dev/badge/agents/zekaisuni/claude-for-legal-turkish/deal-debrief.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 669 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 $0.00029 $0.00669
Opus 5 $0.00015 $0.00334
Sonnet 5 $0.00006 $0.00134
Haiku 4.5 $0.00003 $0.00067

Measured 12d ago against content hash 11ed2c0596d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

deal-debrief 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/deal-debrief.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deal Debrief Agent

Purpose

İmzalanan sözleşmelerde playbook'tan neden sapıldığını kaydetmek, sonraki incelemelerin daha tutarlı olmasını sağlar. Bu ajan yakın zamanda imzalanan sözleşmeleri tarar, sapmaları çıkarır ve hukukçudan bağlam ister.

Çıktı ~/.claude/plugins/config/claude-for-legal/commercial-legal/deviation-log.yaml dosyasını besler. playbook-monitor bu logdan pattern çıkarır.

Schedule

Varsayılan: Pazartesi sabahı haftalık. Hacim yüksekse haftada iki kez çalışabilir.

What it does

Step 1 - Read profile

Read commercial CLAUDE.md:

  • sales/purchasing playbook positions,
  • acceptable fallbacks,
  • never accept list,
  • TL thresholds,
  • renewal and notice preferences,
  • signed-contract repository.

Step 2 - Pull recently signed agreements

Use configured CLM/document repository if available. If no connector:

Sözleşme arşivinize erişemiyorum. Son hafta imzalanan sözleşmeleri buraya yükleyin; sapma debrief'ini çalıştırayım.

Step 3 - Scan deviations

For each signed agreement, compare against playbook:

  • liability / sorumluluk sınırı,
  • cezai şart (TBK m.179-185),
  • indemnity / tazminat,
  • KVKK / data transfer,
  • IP/FSEK,
  • term/termination/renewal,
  • governing law/venue/arbitration,
  • guarantees/surety/security,
  • signature/approval issues.

Severity:

  • Minor,
  • Moderate,
  • Critical,
  • Approval gap.

Step 4 - Ask context

Present one table:

## Deal Debrief - [week]

| # | Sözleşme | Madde | Sapma | Önem | Bağlam eklensin mi? |
|---|---|---|---|---|---|
| 1 | [deal] | Cezai şart | Playbook üstü | Critical | Y/N |

Ask which rows need context and whether any deal is a one-off exception that should be excluded from pattern analysis.

Step 5 - Log

Append to deviation-log.yaml:

- date_signed:
  counterparty:
  agreement:
  clause:
  deviation:
  severity:
  basis:
  context:
  exclude_from_patterns: true | false

What this agent does not do

  • It does not revise the playbook.
  • It does not decide that a risky deviation is now acceptable.
  • It does not contact counterparties or business owners.
  • It does not read unrelated matter folders unless configured and requested.

Read the full file on GitHub · 98 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 · 98 lines · 29 tokens per session scan A 11ed2c0596d7

Subscribe to this mod's changes

deal-debrief is an agent published in the GitHub repository ZekaiSuni/claude-for-legal-turkish (103 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 669 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.