contract

contract is a command for Claude Code from Floka-as/floka-marketplace. It costs 29 tokens per session (2,470 once invoked), scanned A, original, MIT.

A command for writing a detailed development specification before implementation begins. It guides discussion of the desired behavior, user experience, risks, and important decisions so another agent can build from the result.

In plain words
What is it for?
Use it to explore a request, research relevant details, capture decisions, and produce a specification covering enough behavior and context for implementation.
Why use it?
It reduces the chance that an autonomous builder follows a shallow checklist while missing the intended outcome. The process separates product decisions from technical choices that can be worked out by inspecting the codebase.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the forge plugin — 1 skill, 6 commands shipped together

Good fit Use it to explore a request, research relevant details, capture decisions, and produce a specification covering enough behavior and context for implementation.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/floka-as/floka-marketplace/contract
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/Floka-as/floka-marketplace

Made for: Claude Code.

Or install forge, the plugin that ships this one along with the rest of its 1 skill, 6 commands.

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 contract

README.md
[![agentmods](https://agentmods.dev/badge/commands/floka-as/floka-marketplace/contract/github.svg)](https://agentmods.dev/commands/floka-as/floka-marketplace/contract)
Your own site
<a href="https://agentmods.dev/commands/floka-as/floka-marketplace/contract"><img src="https://agentmods.dev/badge/commands/floka-as/floka-marketplace/contract/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 contract

Your own site · 80×15
<a href="https://agentmods.dev/commands/floka-as/floka-marketplace/contract"><img src="https://agentmods.dev/badge/commands/floka-as/floka-marketplace/contract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,470 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 $0.00029 $0.02470
Opus 5 $0.00015 $0.01235
Sonnet 5 $0.00006 $0.00494
Haiku 4.5 $0.00003 $0.00247

Measured 10d ago against content hash b1628d868bc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

contract 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 10d 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.

forge/commands/contract.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forge: Contract (Spec)

You are a thinking partner helping produce a development spec. The spec is the most important artifact in the Forge workflow — it's where quality comes from. An autonomous builder with a good spec builds the right thing. A builder with a thin checklist builds something that passes checkboxes but misses intent.

Invest here. Better to spend 30 minutes on the spec than 2 hours fixing what a thin spec produced.

Philosophy

User = visionary. Claude = builder.

The user knows:

  • How they imagine it working
  • What it should look/feel like
  • What's essential vs nice-to-have
  • Specific behaviors or references they have in mind

The user doesn't know (and shouldn't be asked):

  • Codebase patterns (you read the code)
  • Technical risks (you identify these)
  • Implementation approach (you figure this out)
  • Performance optimization details

Ask about vision and behavior. Don't ask about implementation.

Process

Phase 1: Understand & Explore

  1. Understand the request: Read the user's description. What are they actually trying to achieve? What's the user-facing outcome?

  2. Load prior decisions: Read all existing contracts in .forge/contracts/. Extract decisions that may be relevant to this new work:

    • Established patterns ("card layout" was chosen for entity views)
    • Architecture decisions ("LLM-based extraction, not regex")
    • Rejected approaches ("we tried X and reverted because Y")
    • Carry forward anything applicable. Don't re-ask what's already been decided unless this work has conflicting needs.
  3. Deep code exploration (scout): Don't skim — read the relevant files, understand current patterns, trace the data flow. Build an internal map of:

    • Reusable assets — existing components, hooks, utilities, helpers that could be used
    • Established patterns — how the codebase does state management, styling, data fetching, API design, error handling
    • Integration points — where new code would connect (routes, nav, providers, configs)
    • Adjacent code that will be affected
    • Annotate findings for use in gray-area presentation (e.g., "Card component exists with shadow/rounded variants")

Read the full file on GitHub · 200 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. 10d ago First seen · 200 lines · 29 tokens per session scan A b1628d868bc5

Subscribe to this mod's changes

contract is a command published in the GitHub repository Floka-as/floka-marketplace (7 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 2,470 once invoked, about $0.0001 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.