flat-fee-calculator

flat-fee-calculator is a skill for Claude Code from protomated/protomated-plugins-official. It costs 95 tokens per session (2,583 once invoked), scanned A, original, Apache-2.0.

A calculator that compares hourly billing with fixed-price billing for work completed faster with AI tools. It uses the task time, hourly rate, and number of matters to create a pricing model and CSV file.

In plain words
What is it for?
Use it to model pricing for tasks such as an NDA review or an uncontested divorce document package, then open the resulting CSV in Excel, Google Sheets, or Numbers.
Why use it?
It shows how reduced working time can change revenue under hourly billing and helps test alternative fixed prices. The model keeps the assumptions visible for review.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the flat-fee-calculator plugin — 1 skill shipped together

Good fit Use it to model pricing for tasks such as an NDA review…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/protomated/protomated-plugins-official/flat-fee-calculator
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 protomated/protomated-plugins-official --skill flat-fee-calculator
Clone the repo
git clone --depth 1 https://github.com/protomated/protomated-plugins-official

Made for: Claude Code.

Or install flat-fee-calculator, the plugin that ships this one along with the rest of its 1 skill.

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 flat-fee-calculator

README.md
[![agentmods](https://agentmods.dev/badge/skills/protomated/protomated-plugins-official/flat-fee-calculator.svg)](https://agentmods.dev/skills/protomated/protomated-plugins-official/flat-fee-calculator)
Your own site
<a href="https://agentmods.dev/skills/protomated/protomated-plugins-official/flat-fee-calculator"><img src="https://agentmods.dev/badge/skills/protomated/protomated-plugins-official/flat-fee-calculator.svg" alt="Measured on agentmods" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,583 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 $0.00095 $0.02583
Opus 5 $0.00048 $0.01291
Sonnet 5 $0.00019 $0.00517
Haiku 4.5 $0.00010 $0.00258

Measured 6d ago against content hash 66f7ce83c954, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

flat-fee-calculator 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 6d 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.

flat-fee-calculator/skills/flat-fee-calculator/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/flat-fee-calculator — AI-Adjusted Flat-Fee Repricing Calculator

⚠️ AI-ASSISTED DRAFT — ATTORNEY REVIEW REQUIRED This output was generated by an AI assistant. It is a pricing and business model, not legal advice and not an opinion on what your state bar's fee-reasonableness rules permit. Review the numbers and assumptions before using them to set client pricing.

Hourly billing structurally punishes AI-driven efficiency gains: if a task that used to take two hours now takes forty minutes, hourly billing hands the client an unrequested discount instead of letting the firm capture any of the time saved. This skill builds a revenue model — current hourly, AI-accelerated hourly, and several flat-fee scenarios — from numbers the attorney supplies, and outputs a CSV file the attorney can open in Excel, Google Sheets, or Numbers.

This skill reads files only unless the attorney confirms a save. It does not change any billing system, rate, or client agreement.

Invocation

/flat-fee-calculator [task or matter type]
/flat-fee-calculator "standard NDA review"
/flat-fee-calculator "uncontested divorce document package"

Workflow

Step 1 — Gather inputs

Ask the attorney for, or infer from the argument:

  1. Task or matter type being modeled — specific enough to have a consistent time estimate (e.g., "initial consultation memo," not "family law" broadly).
  2. Current hourly rate ($/hour).
  3. Typical time before using AI tools (hours, e.g. "2.5 hrs").
  4. Typical time after using AI tools (hours) — including this kit's own skills where relevant (e.g., /intake-summary, /billing-narrative, /engagement-letter cutting drafting time).
  5. Matter volume — how many of this task/matter type per month or year. Ask which period and keep the model consistent with it.

Optional — grounding the estimate in real data: if a matter folder or workspace is attached, use the Filesystem connector to search for saved billing-narrative output or time entries mentioning the task type keyword, to sanity-check the attorney's before/after estimates. This is a cross-check, not a replacement — always ask the attorney to confirm or adjust the final numbers before modeling. If nothing is found, proceed directly with the attorney's estimates.

Read the full file on GitHub · 161 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. 6d ago First seen · 161 lines · 95 tokens per session scan A 66f7ce83c954

Subscribe to this mod's changes

flat-fee-calculator is a skill published in the GitHub repository protomated/protomated-plugins-official (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 95 tokens to every session and 2,583 once invoked, about $0.0005 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.

Related

Other skills, from other repositories