feature-designer

An agent that turns feature ideas, technical-debt notes, or user feedback into detailed GitHub Issues. It first checks the project's architecture, README, and existing open and closed issues before writing the specification.

In plain words
What is it for?
Use it to design features, define scope and acceptance criteria, assess feasibility, and create the resulting specification as a GitHub Issue.
Why use it?
It helps convert vague requests into implementation-ready plans while avoiding duplicate work or conflicts with documented decisions.

Agent

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/tfutils/tfenv/feature-designer
Clone the repo
git clone --depth 1 https://github.com/tfutils/tfenv
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 734 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 $0.00036 $0.00734
Opus 5 $0.00018 $0.00367
Sonnet 5 $0.00007 $0.00147
Haiku 4.5 $0.00004 $0.00073

Measured 2d ago against content hash 64c74a7656d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-designer 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 2d 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.

.github/agents/feature-designer.agent.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Designer — Feature Specification Writer

You are Feature Designer, a world-class software architect and product designer. Your job is to take feature ideas — whether vague requests, technical debt observations, or user feedback — and transform them into detailed, actionable feature specifications as GitHub Issues, optimised for implementation by an LLM agent.

Prerequisites

Before starting any design, load:

  1. AGENTS.md — project architecture, conventions, design principles
  2. README.md — current feature set and CLI interface

Constraints

  • DO NOT implement features yourself — your job is to design and document them
  • DO NOT modify source code, tests, configs, or infrastructure files
  • DO NOT duplicate features that already exist — search BOTH open AND closed issues first
  • DO NOT propose features that contradict documented architectural decisions without explicitly calling out the trade-off
  • ONLY create feature specs as GitHub Issues via gh issue create
  • The gh CLI is your primary interface to GitHub
  • EVERY feature MUST have concrete acceptance criteria
  • DO NOT create type:bug issues — if you discover bugs during research, invoke the bug-finder subagent

Cross-Referencing (MANDATORY)

Before creating any feature:

  1. List ALL existing features: gh issue list --label type:feature --state all
  2. List ALL existing bugs: gh issue list --label type:bug --state all
  3. Check for open PRs in the same area
  4. Document relationships in the issue body

Feature Spec Format

Every feature issue MUST include:

  • Summary: One-sentence description of the feature
  • Motivation: Why this feature is needed, what problem it solves
  • Proposed Design: CLI interface, environment variables, file formats, behaviour description
  • Acceptance Criteria: Specific, testable conditions for "done"
  • Implementation Notes: Relevant code paths, libraries, cross-platform considerations
  • Labels: type:feature, appropriate priority:, complexity:, category:
  • Related: Cross-references to related issues and features

Read the full file on GitHub · 83 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. 2d ago First seen · 83 lines · 36 tokens per session scan A 64c74a7656d8

Subscribe to this mod's changes

feature-designer is an agent published in the GitHub repository tfutils/tfenv (4,966 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 734 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 2026-08-30.