proposal

proposal is a skill for Claude Code from Doris-Labs/sales-skills. It costs 74 tokens per session (1,316 once invoked), scanned A, original, MIT.

A method for writing a buyer-specific proposal, statement of work, or quote. A statement of work is a document that defines the agreed work, scope, and terms.

In plain words
What is it for?
Use it to describe the problem, outcome, solution, included and excluded work, pricing, terms, and one next step.
Why use it?
It keeps the document tied to the buyer's stated problem and desired result instead of filling it with unrelated sales material.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sales-skills plugin — 30 skills shipped together

Good fit Use it to describe the problem, outcome, solution, included and excluded work, pricing, terms, and one next step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/doris-labs/sales-skills/proposal
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 Doris-Labs/sales-skills --skill proposal
Clone the repo
git clone --depth 1 https://github.com/Doris-Labs/sales-skills

Made for: Claude Code.

Or install sales-skills, the plugin that ships this one along with the rest of its 30 skills.

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 proposal

README.md
[![agentmods](https://agentmods.dev/badge/skills/doris-labs/sales-skills/proposal/github.svg)](https://agentmods.dev/skills/doris-labs/sales-skills/proposal)
Your own site
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/proposal"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/proposal/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 proposal

Your own site · 80×15
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/proposal"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/proposal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,316 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 $0.00074 $0.01316
Opus 5 $0.00037 $0.00658
Sonnet 5 $0.00015 $0.00263
Haiku 4.5 $0.00007 $0.00132

Measured 9d ago against content hash e099b0864dae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

proposal 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/proposal/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Proposal

Purpose

Turn an established deal into a proposal the buyer recognizes as theirs — built around their stated problem and desired outcome, scoped to what they actually need, priced clearly, and ending in a single next step. Not a template with their logo on it.

Inputs

  • The buyer's stated problem and desired outcome (their words)
  • The solution and scope you're proposing (what's in, what's out)
  • Pricing, and any commercial terms (term length, payment, start date)
  • Who the proposal is for (economic buyer, champion) and what they care about

Method

  1. Pull the buyer's own priorities first. A proposal is a mirror, not a brochure — lead with their stated problem and desired outcome in their language before you describe anything you sell.
  2. Build the proposal on this seven-part spine, in order:
    1. Problem — the buyer's situation and the cost of the status quo, in their words.
    2. Desired outcome — what success looks like to them, stated as their goal.
    3. Solution — how your offering produces that outcome. Tie each capability to a pain or value driver they named. Cut anything that maps to neither.
    4. Scope — exactly what's included, deliverables, and what's explicitly out. Ambiguity here is where deals stall in legal and procurement.
    5. Pricing — clear line items, the total, and the value metric behind it. Anchor against the cost of inaction from step 1, not against competitors.
    6. Terms — term length, payment schedule, start date, key assumptions.
    7. Next steps — one clear CTA (see rule below).
  3. Mirror their words throughout. If they said "ramp time for new reps," don't rewrite it as "onboarding efficiency." Echoing their language is what makes a proposal feel bespoke instead of generic.
  4. Make the next step a single clear CTA — "sign here," "intro to procurement," or "30-min commercial review on ." Multiple asks dilute to zero.

Proposal structure template:

<Title> — Proposal for <Account>

1. The problem
   <their situation + cost of status quo, their words>

2. Desired outcome
   <what success looks like to them>

3. Proposed solution
   <capability> → solves <pain they named>
   <capability> → delivers <value driver they named>

4. Scope
   Included: <deliverables>
   Not included: <explicit exclusions>

5. Investment
   <line item> .......... <price>
   Total: <total> (<value metric / term>)

6. Terms
   Term: <length> | Payment: <schedule> | Start: <date>

7. Next step
   <single clear CTA> by <date>

Read the full file on GitHub · 115 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 · 115 lines · 74 tokens per session scan A e099b0864dae

Subscribe to this mod's changes

proposal is a skill published in the GitHub repository Doris-Labs/sales-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 1,316 once invoked, about $0.0004 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.