draft-offer

draft-offer is a skill for Claude Code from nota-america/forgecat-agent-profiles. It costs 53 tokens per session (603 once invoked), scanned A, a copy of draft-offer, Apache-2.0.

A draft offer letter that brings together a candidate's role, start date, reporting line, location, employment type, salary, equity, bonus, and other terms.

In plain words
What is it for?
Use it to prepare offer-letter text, assemble total compensation details, and give hiring managers negotiation guidance.
Why use it?
It gives hiring teams a clear starting document for presenting an employment offer. It also helps organise the full compensation package in one place.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Good fit Use it to prepare offer-letter text, assemble total compensation details, and give hiring managers negotiation guidance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nota-america/forgecat-agent-profiles/draft-offer
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 nota-america/forgecat-agent-profiles --skill draft-offer
Clone the repo
git clone --depth 1 https://github.com/nota-america/forgecat-agent-profiles

Made for: Claude Code.

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 draft-offer

README.md
[![agentmods](https://agentmods.dev/badge/skills/nota-america/forgecat-agent-profiles/draft-offer/github.svg)](https://agentmods.dev/skills/nota-america/forgecat-agent-profiles/draft-offer)
Your own site
<a href="https://agentmods.dev/skills/nota-america/forgecat-agent-profiles/draft-offer"><img src="https://agentmods.dev/badge/skills/nota-america/forgecat-agent-profiles/draft-offer/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 draft-offer

Your own site · 80×15
<a href="https://agentmods.dev/skills/nota-america/forgecat-agent-profiles/draft-offer"><img src="https://agentmods.dev/badge/skills/nota-america/forgecat-agent-profiles/draft-offer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 603 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 98% 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 $0.00053 $0.00603
Opus 5.5 $0.00021 $0.00241
Sonnet 5.5 $0.00011 $0.00121
Haiku 4.5 $0.00005 $0.00060

Measured 1mo ago against content hash b82ed43ae8d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

draft-offer 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 1mo 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.

Origin

This is a copy

98% identical to draft-offer — 9 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.

profiles/anthropics/knowledge-work-plugins/anthropics_knowledge-work-plugins_human-resources/for-claude/.claude/skills/draft-offer/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/draft-offer

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md (.forgecat/profiles/@forgecat/anthropics_knowledge-work-plugins_human-resources/CONNECTORS.md).

Draft a complete offer letter for a new hire.

Usage

/draft-offer $ARGUMENTS

What I Need From You

  • Role and title: What position?
  • Level: Junior, Mid, Senior, Staff, etc.
  • Location: Where will they be based? (affects comp and benefits)
  • Compensation: Base salary, equity, signing bonus (if applicable)
  • Start date: When should they start?
  • Hiring manager: Who will they report to?

If you don't have all details, I'll help you think through them.

Output

## Offer Letter Draft: [Role] — [Level]

### Compensation Package
| Component | Details |
|-----------|---------|
| **Base Salary** | $[X]/year |
| **Equity** | [X shares/units], [vesting schedule] |
| **Signing Bonus** | $[X] (if applicable) |
| **Target Bonus** | [X]% of base (if applicable) |
| **Total First-Year Comp** | $[X] |

### Terms
- **Start Date**: [Date]
- **Reports To**: [Manager]
- **Location**: [Office / Remote / Hybrid]
- **Employment Type**: [Full-time, Exempt]

### Benefits Summary
[Key benefits highlights relevant to the candidate]

### Offer Letter Text

Dear [Candidate Name],

We are pleased to offer you the position of [Title] at [Company]...

[Complete offer letter text]

### Notes for Hiring Manager
- [Negotiation guidance if needed]
- [Comp band context]
- [Any flags or considerations]

If Connectors Available

If ~~HRIS is connected:

  • Pull comp band data for the level/role
  • Verify headcount approval
  • Auto-populate benefits details

If ~~ATS is connected:

  • Pull candidate details from the application
  • Update offer status in the pipeline

Tips

  1. Include total comp — Candidates compare total compensation, not just base.
  2. Be specific about equity — Share count, current valuation method, vesting schedule.
  3. Personalize — Reference something from the interview process to make it warm.

Read the full file on GitHub · 86 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. 1mo ago First seen · 86 lines · 53 tokens per session scan A b82ed43ae8d6

Subscribe to this mod's changes

draft-offer is a skill published in the GitHub repository nota-america/forgecat-agent-profiles (93 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 603 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to draft-offer, differing in 9 lines, and is treated as a copy.

Related

Other skills, from other repositories

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

longbridge-content

A Longbridge tool for recent stock news, company announcements, regulatory filings, community topics, and analysis of United States SEC filings. SEC filings are official company documents such as annual, quarterly, event, proxy, and insider-trading reports.

longbridge/skills · 203 tokens

revisar-mi-nexo-de-impuesto-sobre-ventas

Descubre dónde debes impuesto sobre ventas. Sumo los ingresos y el número de transacciones por estado de EE. UU. desde Stripe (o QuickBooks / Xero / facturas como respaldo), comparo los totales de cada estado contra su umbral de nexo económico para el trimestre y los últimos 12 meses, identifico el mes exacto en que…

gethouston/houston · 177 tokens

deal-structure-analyst

Compares realistic alternative structures for a transaction — asset purchase versus share purchase, merger versus acquisition, direct investment versus a holding-company route, debt versus equity, onshore versus offshore vehicle — and their legal, tax-flagged, liability, and control consequences, before any drafting…

rohasnagpal/legal-ai-skills · 199 tokens

treaty-analyst

Analyses treaty entitlement and relief on given facts — treaty residency, the applicable income article, beneficial ownership and limitation-of-benefits conditions, and the relief potentially available — flagging every substantive term for verification against the actual treaty text rather than assuming a generic…

rohasnagpal/legal-ai-skills · 171 tokens

sanctions-screening-documenter

Document sanctions screening of customers, counterparties, beneficial owners, controllers, vessels, aircraft, addresses, and transactions against applicable official lists and restrictions. Use for onboarding, periodic or event-driven rescreening, alert disposition, ownership-and-control review, and audit evidence.

rohasnagpal/legal-ai-skills · 60 tokens