sow

sow is a command for Claude Code from jeremylongshore/tons-of-skills-marketplace. It costs 8 tokens per session (667 once invoked), scanned A, original, MIT.

A document template for defining an AI automation project’s work, deliverables, timeline, and responsibilities. A Statement of Work is a formal agreement that records what a project includes and excludes.

In plain words
What is it for?
Creating Statements of Work for AI automation projects, including project summaries, in-scope and out-of-scope work, milestones, testing, deployment, and training.
Why use it?
It gives clients and teams a shared written agreement about the project’s scope, deadlines, and expected results. This helps reduce misunderstandings about what will be delivered.

Command for Claude Code

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

Part of the sow-generator plugin — 1 command shipped together

Good fit Creating Statements of Work for AI automation projects, including project summaries, in-scope and out-of-scope work, milestones, testing, deployment, and training.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jeremylongshore/tons-of-skills-marketplace/sow
About the project

Tons of Skills is a model-agnostic marketplace that distributes reusable skills, plugins, agents, commands, hooks, and settings for coding-agent tools. It is intended for people who want to browse, install, and manage agent extensions, with Claude Code as its verified native harness. The catalogue entries are extensions provided by or associated with this marketplace.

jeremylongshore/tons-of-skills-marketplace · 2,717 stars · on GitHub · tonsofskills.com

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.

Clone the repo
git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace

Made for: Claude Code.

Or install sow-generator, the plugin that ships this one along with the rest of its 1 command.

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 sow

README.md
[![agentmods](https://agentmods.dev/badge/commands/jeremylongshore/tons-of-skills-marketplace/sow/github.svg)](https://agentmods.dev/commands/jeremylongshore/tons-of-skills-marketplace/sow)
Your own site
<a href="https://agentmods.dev/commands/jeremylongshore/tons-of-skills-marketplace/sow"><img src="https://agentmods.dev/badge/commands/jeremylongshore/tons-of-skills-marketplace/sow/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 sow

Your own site · 80×15
<a href="https://agentmods.dev/commands/jeremylongshore/tons-of-skills-marketplace/sow"><img src="https://agentmods.dev/badge/commands/jeremylongshore/tons-of-skills-marketplace/sow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 667 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 $0.00008 $0.00667
Opus 5 $0.00004 $0.00333
Sonnet 5 $0.00002 $0.00133
Haiku 4.5 $0.00001 $0.00067

Measured 9d ago against content hash 95592aca7ef9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sow 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.

plugins/ai-agency/sow-generator/commands/sow.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SOW Generator

Generate professional Statements of Work for AI automation projects.

SOW Template

# STATEMENT OF WORK

## Project Information
- **Client:** [Company Name]
- **Project:** [Project Name]
- **Date:** [Date]
- **Valid Until:** [Date + 30 days]
- **Prepared By:** [Your Agency]

## 1. Project Overview
[Brief description of what will be delivered and why]

## 2. Scope of Work

### In Scope
- Deliverable 1: [Description]
- Deliverable 2: [Description]
- Deliverable 3: [Description]

### Out of Scope
- [What is explicitly not included]
- [Future phase items]

## 3. Deliverables
| Deliverable | Description | Completion Date |
|-------------|-------------|-----------------|
| Discovery & Planning | Detailed requirements document | Week 2 |
| Design & Architecture | Technical design document | Week 4 |
| Development | Working automation system | Week 8 |
| Testing & QA | Test reports and bug fixes | Week 10 |
| Deployment | Live system with documentation | Week 12 |
| Training | User training sessions | Week 13 |

## 4. Timeline
- **Start Date:** [Date]
- **End Date:** [Date]
- **Total Duration:** [X] weeks
- **Key Milestones:**
  - Milestone 1: [Date]
  - Milestone 2: [Date]
  - Milestone 3: [Date]

## 5. Investment
| Item | Cost |
|------|------|
| Discovery & Planning | $X,XXX |
| Development | $XX,XXX |
| Testing & QA | $X,XXX |
| Training | $X,XXX |
| **Total Project Cost** | **$XX,XXX** |

**Payment Terms:**
- 30% upon signing ($X,XXX)
- 40% at development completion ($X,XXX)
- 30% upon final delivery ($X,XXX)

## 6. Client Responsibilities
- Provide access to systems and APIs
- Timely feedback on deliverables
- Designate project stakeholder
- Provide test environment
- User acceptance testing

## 7. Assumptions
- Client has necessary API access
- Required systems have documented APIs
- Test environment will be provided
- Stakeholders available for meetings
- Timely approval of deliverables

## 8. Terms & Conditions
- Changes to scope require written approval
- Additional work billed at $XXX/hour
- Payment terms: Net 15 days
- IP ownership transfers upon final payment
- 30-day warranty on deliverables

## 9. Acceptance Criteria
Project will be considered complete when:
- All deliverables meet specifications
- User acceptance testing passed
- Documentation delivered
- Training completed
- Client signs acceptance form

## Signatures
**Client Approval:**
Name: ___________________
Title: ___________________
Date: ___________________

**Agency Authorization:**
Name: ___________________
Title: ___________________
Date: ___________________

Read the full file on GitHub · 110 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 · 110 lines · 8 tokens per session scan A 95592aca7ef9

Subscribe to this mod's changes

sow is a command published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,717 stars, last pushed today), licensed MIT. It adds 8 tokens to every session and 667 once invoked, about $0.0000 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 2026-09-03.