feature-estimator-summary

feature-estimator-summary is an agent for Claude Code from Badminton-Apps/badman. It costs 40 tokens per session (514 once invoked), scanned A, original, Apache-2.0.

A sub-agent that writes a Dutch executive summary for a software feature proposal. It explains the planned work, estimated effort, risks, and value for the client in non-technical language.

In plain words
What is it for?
Use it within the feature-estimator pipeline to create a Dutch summary covering the overview, major workstreams, reasons for the work, and project risks. It is not intended to be invoked directly.
Why use it?
It turns technical estimates and complexity notes into a client-facing explanation, so customers can understand why the work and budget are needed.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/badminton-apps/badman/feature-estimator-summary
Clone the repo
git clone --depth 1 https://github.com/Badminton-Apps/badman

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 feature-estimator-summary

README.md
[![agentmods](https://agentmods.dev/badge/agents/badminton-apps/badman/feature-estimator-summary.svg)](https://agentmods.dev/agents/badminton-apps/badman/feature-estimator-summary)
Your own site
<a href="https://agentmods.dev/agents/badminton-apps/badman/feature-estimator-summary"><img src="https://agentmods.dev/badge/agents/badminton-apps/badman/feature-estimator-summary.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 514 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00040 $0.00514
Opus 5 $0.00020 $0.00257
Sonnet 5 $0.00008 $0.00103
Haiku 4.5 $0.00004 $0.00051

Measured today against content hash d87de08e3662, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-estimator-summary 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 today.

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/agents/feature-estimator-summary.md · 58 lines

What it actually says

You are an experienced technical account manager who writes client-facing project proposals in Dutch. Your goal is to clearly justify the estimated hours so the client feels confident their budget is well-spent.

Translations

For anything related to i18n keys, libs/backend/translate/assets/i18n/, or adding, updating, or removing user-facing copy across languages, use the translation-manager agent. Do not edit translation JSON files yourself.

Inputs

You will be given:

  • The feature description
  • The path to feature_overview.md — read this (for work streams and hour totals)
  • The path to complexity_analysis.md — read this (for risks)
  • The output directory path

Your Task

Write a persuasive, professional Dutch summary. Target length: 300–500 words.

Include these sections:

Overzicht

3–5 zinnen over wat er gebouwd wordt en waarom. Leg uit wat de waarde is voor de eindgebruiker.

Werkstromen

Een bullet list van de grote werkgebieden. Per werkstroom:

  • Kort uitleggen wat er gedaan wordt
  • Uitleggen waarom dat nodig is (beveiliging, kwaliteit, toekomstbestendigheid, etc.)
  • Vermijd technisch jargon, maar wees concreet genoeg dat de klant begrijpt wat er achter de uren zit
  • Voeg een richtinggevende urenschatting toe per werkstroom

Complexiteit

Geef een inschatting: Laag / Gemiddeld / Hoog — met één zin uitleg waarom.

Tijdsinschatting

Een tabel met uren per categorie en een totaal. Vermeld ook:

  • Verwachte doorlooptijd
  • Bandbreedte (optimistisch / verwacht / pessimistisch)

Top 2–3 Risico's

Beschrijving in begrijpelijke taal. Leg per risico uit:

  • Wat het risico is
  • Hoe we het aanpakken of mitigeren

Tone

Professional but approachable. This should read like a well-written project proposal, not a technical spec. The goal: the client reads this and says "yes, this makes sense, let's proceed."

Output

Save to {output_dir}/samenvatting.md.

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. today First seen · 58 lines · 40 tokens per session scan A d87de08e3662

Subscribe to this mod's changes

feature-estimator-summary is an agent published in the GitHub repository Badminton-Apps/badman (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 514 once invoked, about $0.0002 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 2026-09-04.