deal-desk

deal-desk is a skill for Codex from bestagentkits/agency-skills. It costs 164 tokens per session (2,726 once invoked), scanned A, a copy of deal-desk, MIT.

A deal-review assistant for evaluating individual sales deals before they close. It scores commercial risk, checks contract terms, and sends approval decisions to the appropriate human.

In plain words
What is it for?
Use it to review discounts, calculate deal economics, route approval requests, and identify risky contract clauses with suggested counters.
Why use it?
It makes discount, margin, payment, indemnity, and contract risks visible before someone approves the deal. It also prevents the system from approving deals automatically.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex; mentions Gemini CLI; mentions OpenCode.

Good fit Use it to review discounts, calculate deal economics, route approval requests, and identify risky contract clauses with suggested counters.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bestagentkits/agency-skills/deal-desk
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 bestagentkits/agency-skills --skill deal-desk
Clone the repo
git clone --depth 1 https://github.com/bestagentkits/agency-skills

Made for: 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 deal-desk

README.md
[![agentmods](https://agentmods.dev/badge/skills/bestagentkits/agency-skills/deal-desk/github.svg)](https://agentmods.dev/skills/bestagentkits/agency-skills/deal-desk)
Your own site
<a href="https://agentmods.dev/skills/bestagentkits/agency-skills/deal-desk"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/deal-desk/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-desk

Your own site · 80×15
<a href="https://agentmods.dev/skills/bestagentkits/agency-skills/deal-desk"><img src="https://agentmods.dev/badge/skills/bestagentkits/agency-skills/deal-desk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,726 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 92% copy Near-identical to another mod 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 $0.00164 $0.02726
Opus 5 $0.00082 $0.01363
Sonnet 5 $0.00033 $0.00545
Haiku 4.5 $0.00016 $0.00273

Measured 9d ago against content hash 39dcfb0d5098, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

deal-desk 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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/deal_scorer.py, scripts/discount_approval_router.py, scripts/terms_redliner.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

92% identical to deal-desk — 7 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/claude-skills/deal-desk/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

deal-desk

Per-deal review and discount-approval routing. Scores deal margin + risk, routes discount approval to the right human, redlines T&Cs against commercial policy. Never auto-approves. Every output is a score plus a routing recommendation to a named human approver.

Purpose

Deal Desk / RevOps / sales leadership live at the moment between sales-team-asks-for-discount and CFO/CRO/legal-signs. This skill quantifies the asks and routes them.

Three deterministic tools:

  1. deal_scorer.py — Scores a deal 0-100 across 5 dimensions (margin, risk, strategic value, commercial fit, term shape) and assigns one of four verdicts: APPROVE / REVIEW / ESCALATE / DECLINE — each tied to a named approver chain.
  2. discount_approval_router.py — Maps a discount-percent + deal-size + tier to a named approver chain (AE → Manager → Director → VP → CFO/CRO) with estimated cycle days. Honors industry-tuned policy bands.
  3. terms_redliner.py — Detects 10 founder/seller-killer patterns in deal terms (uncapped indemnity, MFN, perpetual license-back, missing DPA, NET-60+, broad non-solicit, etc.) with severity + standard counter + named legal/commercial approver.

When to use

Invoke this skill when:

  • Sales has flagged a discount request above AE authority.
  • A customer has returned a redlined MSA and you need triage before routing to legal.
  • The deal needs CFO sign-off and you want a defensible margin breakdown.
  • An RFP response requires multi-year terms and you need to score the shape.
  • A renewal expansion is bundled with a discount and you need to verify policy fit.
  • You're building a deal-desk approval queue and need consistent routing.

Do NOT use this skill to: author the proposal (use business-growth/contract-and-proposal-writer), redesign the discount matrix (use the commercial-policy sibling skill), or do deep legal redline of full contract text (use c-level-advisor/skills/general-counsel-advisor).

Workflow

  1. Intake the deal — Sales/AE fills assets/deal_intake_template.md with ARR, term, discount, payment terms, customer tier, strategic flags, and any customer-flagged term redlines (20-min fill-out).
  2. Score margin + risk — Run deal_scorer.py --input deal.json --profile {saas|enterprise-software|services|marketplace}. Read the composite + per-dimension breakdown + verdict.
  3. Route the discount — Run discount_approval_router.py --input deal.json --profile <same>. Get the named approver chain + estimated cycle days. Modifiers (enterprise floor, SMB fast-lane) are surfaced explicitly.
  4. Flag the redlines — Run terms_redliner.py --input deal_terms.json. Get ranked CRITICAL/HIGH/MEDIUM/LOW findings with the counter-language and the approver who must sign each.
  5. Assemble the packet — Combine the three outputs into a deal-desk review packet. Always include the named approver chain. The packet is a recommendation, not an approval.

Read the full file on GitHub · 139 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 139 lines · 164 tokens per session scan A 39dcfb0d5098

Subscribe to this mod's changes

deal-desk is a skill published in the GitHub repository bestagentkits/agency-skills (11 stars, last pushed 2mo ago), licensed MIT. It adds 164 tokens to every session and 2,726 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to deal-desk, differing in 7 lines, and is treated as a copy.

Related

Other skills, from other repositories

thai-invoice

Use this skill for any task involving Thai tax invoices, receipts, quotations, or withholding-tax certificates. Trigger whenever the user asks to: draft a Thai tax invoice (ใบกำกับภาษี), receipt (ใบเสร็จ), quotation (ใบเสนอราคา), credit/debit note (ใบลดหนี้/ใบเพิ่มหนี้), or WHT certificate (ภ.ง.ด.3/53). Also trigger…

Boom-Vitt/claude-thai-skills · 158 tokens

contract-reviewer

Reviews MSA and order form terms for red flags, risk levels, and suggested counter-language.

Autter-dev/agentic-sales-skills · 22 tokens

ai-financial-marketing-compliance-review

A financial marketing compliance review assistant for examining pricing or marketing material for financial concerns.

skillsaiagent/aiskills · 79 tokens

ai-insurance-policy-faq-explainer

A risk-review helper for explaining questions about insurance policies and their possible risks. It produces summaries, diagnoses, recommended actions, and reusable deliverables from supplied material.

skillsaiagent/aiskills · 74 tokens

expense-review-policy

Review invoices and contracts against accounts-payable policy before human approval.

openai/openai-cookbook · 17 tokens

kyc-doc-parse

Parse an investor or client onboarding packet into structured KYC fields — identity, ownership, control, source of funds, and document inventory. Use as the first step of KYC screening; output feeds the rules engine.

anthropics/financial-services · 49 tokens