agentmods.dev

proposal-writing

proposal-writing is a skill for Claude Code from MarcoZorn/agencykit. It costs 27 tokens per session (699 once invoked), scanned A, original, MIT.

A proposal-writing guide that drafts a client-facing offer from the project scope, budget, deadline and optional examples of earlier work.

In plain words
What is it for?
Use it to prepare proposals for new pitches or scoped projects. Review all prices, commitments and default terms before sending.
Why use it?
It organises deliverables, timing, pricing and terms in one draft while separating internal assumptions, risks and margin notes from text meant for the client.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions Codex; built for openclaw.

not rated 6repo 4mo ago A scan 27 tokens original MIT

Good fit Use it to prepare proposals for new pitches or scoped projects. Review all prices, commitments and default terms before sending.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marcozorn/agencykit/proposal-writing
View source ↗ MarcoZorn/agencykit marcozorn.github.io
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 MarcoZorn/agencykit --skill proposal-writing
Clone the repo
git clone --depth 1 https://github.com/MarcoZorn/agencykit

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 proposal-writing

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcozorn/agencykit/proposal-writing"><img src="https://agentmods.dev/badge/skills/marcozorn/agencykit/proposal-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 699 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 $0.00027 $0.00699
Opus 5.5 $0.00011 $0.00280
Sonnet 5.5 $0.00005 $0.00140
Haiku 4.5 $0.00003 $0.00070

Measured 2mo ago against content hash f4a4e8895376, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

proposal-writing 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 2mo 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.

.claude/skills/proposal-writing/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

proposal-writing

When to use this skill

EN triggers: "proposal", "write a proposal", "client proposal", "new pitch", "scope document" IT triggers: "proposta", "scrivi una proposta", "pitch", "documento di scopo"

Inputs required

Before generating, ask:

  1. Client name and industry
  2. Service scope (what will be delivered)
  3. Budget range (or "unknown")
  4. Deadline for the proposal
  5. Do you have past proposals or scope/outcome examples to reference? (optional but recommended)

Output format

Produces two blocks:

CLIENT-FACING PROPOSAL

  • Executive summary (2-3 sentences, outcome-focused)
  • Scope of work (phased, specific)
  • Deliverables list
  • Timeline
  • Investment (pricing table)
  • Payment terms (default: 50% upfront, 50% on delivery)
  • Revision policy (2 included, extras billed separately)
  • Next steps / CTA

INTERNAL NOTE (do not send)

  • Margin estimate if budget provided
  • Assumptions made
  • Risks flagged

Human gate

This output is a draft. Review all pricing, scope, and commitment language before sending to the client. Do not send automatically.

Brand voice

If a BRAND.md file exists in .claude/skills/proposal-writing/ or .claude/brand/, read it before generating and apply its tone, terminology, and examples throughout the proposal.

Past proposal reference

If the user provides past proposals or scope/outcome example pairs, extract:

  • Tone and structure patterns
  • Pricing conventions
  • How scope was framed Apply these patterns to the new proposal without copying verbatim.

Edge cases

  • If budget is unknown: produce the proposal with a [TBD] placeholder and a note to fill before sending
  • If scope is vague: ask one clarifying question before proceeding
  • If past examples conflict: use the most recent one as primary reference

🇮🇹 Versione italiana

Quando usare questa skill

Frasi trigger: "proposta", "scrivi una proposta", "pitch cliente", "documento di scopo"

Input necessari

Prima di generare, chiedi:

  1. Nome e settore del cliente
  2. Scope del servizio
  3. Budget indicativo (o "non definito")
  4. Deadline per la proposta
  5. Hai proposte precedenti o esempi scope/outcome da usare come riferimento? (opzionale ma consigliato)

Read the full file on GitHub · 82 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. 2mo ago First seen · 82 lines · 27 tokens per session scan A f4a4e8895376

Subscribe to this mod's changes

proposal-writing is a skill published in the GitHub repository MarcoZorn/agencykit (6 stars, last pushed 4mo ago), licensed MIT. It adds 27 tokens to every session and 699 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude CodeMarketing and SEOWriting and docsagencyagent-skillsai-toolsclaudeclientcreative-agencyproposalsales
Related

proposal-writing compared with skills from other repositories

proposal-writing next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
proposal-writingMarcoZorn/agencykitSkill64mo agoMITA27Claude Code
geo-proposalzubair-trabzada/geo-seo-claudeSkill12ktodayMITA83Claude Code
geo-proposalasale-ai/seo-geo-skillSkill62mo agononeA83Claude Code
geo-proposaltechhorizonlabs/thl-openSkill191mo agoMITA83Claude Code
geo-proposalmultiplex-ai/muggle-ai-teamsSkill219d agoMITA83Claude Code
proposal-writerclaude-office-skills/skillsSkill5759mo agoMITA13Claude Code, Codex
proposal-generatorAutter-dev/agentic-sales-skillsSkill46mo agoMITA21Claude Code, Codex