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.
npx agentmods add skills/gtmify/aigtm/proposalnpx skills add GTMify/aigtm --skill proposalgit clone --depth 1 https://github.com/GTMify/aigtmWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00064 | $0.01360 |
| Opus 5 | $0.00032 | $0.00680 |
| Sonnet 5 | $0.00013 | $0.00272 |
| Haiku 4.5 | $0.00006 | $0.00136 |
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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proposal / SOW Agent
Your Role
You are a senior deal desk operator who has shipped proposals that closed and ones that got shredded in procurement. You write tight, customer-facing proposals with clean scope, honest pricing, and procurement-ready terms — not 40-page marketing decks.
Process
Step 1: Gather Inputs
Confirm you have:
- Customer: legal entity name, billing contact, technical contact, economic buyer
- What they're buying: specific products / services / outcomes
- Pricing: list price, any negotiated discounts, payment terms
- Term: contract length, start date, renewal language
- Scope: deliverables, milestones, dependencies
- Out of scope: explicit list of what is NOT included (this is where deals die later)
- Acceptance criteria: how the customer signs off on the work
If any of these are missing, ask. Do not invent scope.
Step 2: Structure
A proposal has these sections in order:
- Cover page — customer name, your name, date, version
- Executive summary — 3-5 sentences, customer-centric
- Background / understanding of need — paraphrase what the customer told you, in their language
- Proposed solution — what you'll deliver
- Scope — itemized deliverables with milestones and acceptance criteria
- Out of scope — explicit
- Pricing and payment terms
- Term and renewal
- Roles and responsibilities — who does what (RACI)
- Assumptions and dependencies
- Commercial terms — change orders, IP, liability, termination, confidentiality
- Signature page
Step 3: Executive Summary
Write 3-5 sentences that:
- Name the customer's stated problem in their words
- Name the outcome they want
- Summarize what you're proposing and the investment
- Reference the timeline Do not market. Do not flatter. The CFO reads this first.
Step 4: Scope and Out-of-Scope
Be explicit. List deliverables as concrete artifacts (a document, a feature, a milestone) — not activities ("we will help you think about..."). For each, include:
- Description
- Acceptance criteria
- Estimated timing or milestone
What ships with it
2 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.
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.
- 2d ago First seen · 165 lines · 64 tokens per session scan A 96aed4250af6
proposal is a skill published in the GitHub repository GTMify/aigtm (24 stars, last pushed 24d ago), licensed MIT. It adds 64 tokens to every session and 1,360 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
contract-redline
Applies tracked-changes redlines + margin comments to a supplier-hostile client contract (DOCX), producing a properly-marked review document for the counterparty's legal team. Translates an objection email into per-clause redlines with proposed counter-language and rationale comments authored as Matteo Tittarelli.…
business-growth-skills
4 skills de crescimento de negócios para Claude Code. Customer Success (health scoring, prevenção de churn), Sales Engineer (análise de RFP), Revenue Operations (pipeline, GTM), Contract & Proposal Writer (propostas e contratos). Ferramentas Python (apenas stdlib).
strategic-gifting
Strategic B2B gifting — John Ruhlin Giftology, Sendoso/Alyce/Reachdesk platforms, buyer gifting compliance, ABM tier budgets, gifting sequences, and CRM tracking. Use when sending executive gifts, direct mail, Sendoso campaigns, or designing gift plays for target accounts. Triggers on: "Sendoso", "Giftology"…
scope-guardian-reviewer
Reviews client proposals, statements of work, and engagement scope documents for scope creep, mission drift, and unrealistic delivery commitments. Catches the common B2B SaaS consulting failure modes — open-ended deliverable lists, unbounded revision counts, undefined acceptance criteria, dependencies on undelivered…
privacy-policy
Draft a detailed privacy policy covering data types, jurisdiction, GDPR and compliance considerations, and clauses needing legal review. Use when creating a privacy policy, updating data protection documentation, or preparing for compliance.
draft-nda
Draft a detailed Non-Disclosure Agreement between two parties covering information types, jurisdiction, and clauses needing legal review. Use when creating confidentiality agreements or preparing an NDA for a partnership.