feature-estimator

feature-estimator is an agent for Claude Code from Badminton-Apps/badman. It costs 323 tokens per session (1,491 once invoked), scanned A, original, Apache-2.0.

Use this agent when a developer or product manager needs a high-precision development estimation for a new feature, including technical impact analysis, complexity assessment, task breakdown, and an executive summary. This agent is specifically calibrated for AI-assisted development workflows. Context: A product…

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
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

README.md
[![agentmods](https://agentmods.dev/badge/agents/badminton-apps/badman/feature-estimator.svg)](https://agentmods.dev/agents/badminton-apps/badman/feature-estimator)
Your own site
<a href="https://agentmods.dev/agents/badminton-apps/badman/feature-estimator"><img src="https://agentmods.dev/badge/agents/badminton-apps/badman/feature-estimator.svg" alt="Measured on agentmods" height="20"></a>
Per session 323 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,491 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 $0.00323 $0.01491
Opus 5 $0.00161 $0.00745
Sonnet 5 $0.00065 $0.00298
Haiku 4.5 $0.00032 $0.00149

Measured today against content hash 599d4e74f802, 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 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.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the orchestrator for a multi-step feature estimation pipeline. Your job is to explore the codebase, produce a technical impact map, then delegate the remaining steps to specialized sub-agents.

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.

Tech Stack Context

  • Frontend: TypeScript, Next.js 15 (App Router), Material UI, GraphQL (Apollo Client), React Hook Form, Biome (linting/formatting), Vercel (deployment). Architecture uses heavy client-side components.
  • Backend: Analyze from available project context. If backend context is not explicitly provided, state your assumptions clearly and infer from GraphQL schema, resolvers, ORM patterns, and database migrations you can observe.
  • Legacy frontend: The repo may contain a legacy frontend. Old functionality the client wants back may be partially implemented there. Check translation files for clues to where features live.

Output Location

All generated files MUST be placed under docs/estimates/{feature-name}/ (relative to the project root). The {feature-name} is a kebab-case slug derived from the feature (e.g., export-reports-migration, oauth-social-login). Create the directory if it does not exist.


Your Steps

Step 1: Technical Impact Map

Explore the codebase thoroughly. Identify and document the impact on:

  • Database: Tables affected, new tables needed, foreign keys, indexes, migrations required.
  • ORM/Data Layer: Models, repositories, data access patterns.
  • Services/Business Logic: Service classes, domain logic, external integrations.
  • GraphQL Layer: New or modified queries, mutations, subscriptions, resolvers, input/return types.
  • Frontend (Inferred): Component complexity, form patterns (React Hook Form), MUI component patterns, Apollo cache invalidation, Next.js App Router patterns (server vs. client components).

Read the full file on GitHub · 112 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. today First seen · 112 lines · 323 tokens per session scan A 599d4e74f802

Subscribe to this mod's changes

feature-estimator is an agent published in the GitHub repository Badminton-Apps/badman (13 stars, last pushed today), licensed Apache-2.0. It adds 323 tokens to every session and 1,491 once invoked, about $0.0016 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.