Indemnity and Escrow Risk Review

Indemnity and Escrow Risk Review is a skill for Claude Code, Codex from zgbrenner/agentcounsel. It costs 41 tokens per session (3,479 once invoked), scanned A, original, MIT.

A review of the indemnification and escrow terms in an M&A purchase agreement. Indemnification sets out who pays for certain losses after closing, while escrow holds part of the purchase price as security for those claims.

In plain words
What is it for?
It is for examining survival periods, caps, baskets, escrow arrangements, and the order and process for making claims under a purchase agreement.
Why use it?
It makes post-closing risk easier to understand by showing what protections last, what limits apply, and how a party can recover money. It also highlights unclear recovery mechanics for attorney review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for examining survival periods, caps, baskets, escrow arrangements, and the order and process for making claims under a purchase agreement.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zgbrenner/agentcounsel/indemnity-escrow-risk-review
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.

Any agent
npx skills add zgbrenner/agentcounsel --skill indemnity-escrow-risk-review
Clone the repo
git clone --depth 1 https://github.com/zgbrenner/agentcounsel

Made for: Claude Code, Codex.

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 Indemnity and Escrow Risk Review

README.md
[![agentmods](https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/indemnity-escrow-risk-review/github.svg)](https://agentmods.dev/skills/zgbrenner/agentcounsel/indemnity-escrow-risk-review)
Your own site
<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/indemnity-escrow-risk-review"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/indemnity-escrow-risk-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.

agentmods 80×15 button for Indemnity and Escrow Risk Review

Your own site · 80×15
<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/indemnity-escrow-risk-review"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/indemnity-escrow-risk-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,479 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 $0.00041 $0.03479
Opus 5 $0.00020 $0.01740
Sonnet 5 $0.00008 $0.00696
Haiku 4.5 $0.00004 $0.00348

Measured 9d ago against content hash 4b0f56f041fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Indemnity and Escrow Risk 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 9d 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.

skills/m-and-a/indemnity-escrow-risk-review/SKILL.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Indemnity and Escrow Risk Review

Purpose

Analyze the indemnification and escrow architecture of an M&A purchase agreement — a stock purchase agreement, asset purchase agreement, membership-interest purchase agreement, or merger agreement — and surface, from a stated side of the deal, how the agreement allocates post-closing risk: what survives and for how long, what limits and thresholds apply, how an indemnification claim is recovered and in what order, and where the mechanics are unclear.

This skill produces draft work product for attorney review only. It is not legal advice and is not a final negotiating position. The indemnity and escrow package is the heart of post-closing risk allocation; the definitive agreement, as negotiated and signed, controls.

Use When

  • A user asks to "review the indemnity in this purchase agreement," "check the escrow and survival terms," "what should we negotiate on the indemnification package," or "map the recovery mechanics in this SPA."
  • A deal team needs a structured read of the indemnification, escrow, and survival provisions before signing or countering a definitive agreement.
  • The indemnity and escrow architecture of a stock purchase, asset purchase, membership-interest purchase, or merger agreement must be summarized and risk-mapped from one side of the deal.
  • A reviewer needs a recovery waterfall showing the order and limits in which an indemnification claim is satisfied under the agreement.

Required Inputs

  • The agreement's indemnification, escrow, and survival provisions — uploaded or pasted. The full purchase agreement is preferred, since defined terms, the escrow agreement, and disclosure schedules interact with these provisions. Do not review from a description, a summary, or a partial excerpt.
  • The side the review is for — buyer-side or seller-side. Indemnity risk runs in opposite directions for the two; the review must be done from one stated side.
  • The deal type — for example a stock purchase, asset purchase, membership-interest purchase, or merger.
  • Whether representation and warranty insurance (RWI) is in play — and, if so, whether it is intended as the buyer's primary or excess recovery, to the extent the agreement or the user states it.
  • Jurisdiction and governing law — as stated in the agreement, or flagged as unknown.
  • Any related documents — the escrow agreement, the disclosure schedules, or an RWI policy or binder — if they exist.

Read the full file on GitHub · 276 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. 9d ago First seen · 276 lines · 41 tokens per session scan A 4b0f56f041fc

Subscribe to this mod's changes

Indemnity and Escrow Risk Review is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 3,479 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 2026-09-03.

Related

Other skills, from other repositories

fiscaliste

Fiscaliste IA pour la fiscalité personnelle des particuliers français : optimisation et déclaration de l'impôt sur le revenu, IFI, revenus du capital, revenus fonciers, equity salarial, crypto-actifs et PER. Couvre le calcul de l'IR (barème, quotient familial, décote, PAS, CEHR, revenus exceptionnels), la déclaration…

romainsimon/paperasse · 302 tokens

controleur-fiscal

Inspecteur des finances publiques IA. Simule un contrôle fiscal DGFIP complet sur les comptes d'une entreprise française (SASU, EURL, SAS, SARL). Analyse le FEC, la liasse fiscale, les charges déduites, le compte courant d'associé, la TVA, l'IS selon 8 axes de vérification. Identifie les chefs de redressement…

romainsimon/paperasse · 136 tokens

commissaire-aux-comptes

Commissaire aux comptes IA pour l'audit des comptes annuels d'entreprises françaises. Applique la démarche NEP en 7 phases : prise de connaissance, contrôle du FEC, vérification du bilan, du compte de résultat, de la balance, de la liasse fiscale, et contrôles transversaux. Émet une opinion motivée sur la fiabilité…

romainsimon/paperasse · 123 tokens

agb-bei-kreditvertraegen-verbraucherdarlehen

Für AGB bei Kreditverträgen Verbraucherdarlehen: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

Klotzkette/claude-fuer-deutsches-recht · 49 tokens

agb-in-kapitalanlagen-effektenhandel

Für AGB in Kapitalanlagen Effektenhandel: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

Klotzkette/claude-fuer-deutsches-recht · 41 tokens

internal-controls-and-audit

Designs and tests controls over financial reporting — segregation of duties, approval limits, evidence, and preparing for audit. Use this to design controls for a process, prepare for an external audit, respond to an audit finding, set approval thresholds, or assess where a small team's segregation of duties is…

cbrock84/headcount · 67 tokens