feature

feature is a command for Claude Code from nxtg-ai/forge-plugin. It costs 9 tokens per session (2,557 once invoked), scanned A, original, MIT.

An end-to-end feature-building workflow that takes an idea through planning, implementation, testing, and final checks. It uses separate software agents to design the work, write code and tests, and check for errors and security problems.

In plain words
What is it for?
Use it to add a new feature from a description, such as authentication, while producing a plan, implementation, tests, and validation results.
Why use it?
Building a feature usually requires coordinating requirements, code, tests, and review. This puts those stages into one process with checks before the work is finished.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the nxtg-forge plugin — 27 skills, 24 commands, 33 agents shipped together

Good fit Use it to add a new feature from a description, such as authentication, while producing a plan, implementation, tests, and validation results.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add nxtg-ai/forge-plugin
Claude Code
/plugin install nxtg-forge

Made for: Claude Code.

Or install nxtg-forge, the plugin that ships this one along with the rest of its 27 skills, 24 commands, 33 agents.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/nxtg-ai/forge-plugin/feature/github.svg)](https://agentmods.dev/commands/nxtg-ai/forge-plugin/feature)
Your own site
<a href="https://agentmods.dev/commands/nxtg-ai/forge-plugin/feature"><img src="https://agentmods.dev/badge/commands/nxtg-ai/forge-plugin/feature/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 feature

Your own site · 80×15
<a href="https://agentmods.dev/commands/nxtg-ai/forge-plugin/feature"><img src="https://agentmods.dev/badge/commands/nxtg-ai/forge-plugin/feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,557 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 $0.00009 $0.02557
Opus 5.5 $0.00004 $0.01023
Sonnet 5.5 $0.00002 $0.00511
Haiku 4.5 $0.00001 $0.00256

Measured 4d ago against content hash 4e5564702122, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

feature 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 4d 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.

plugins/nxtg-forge/commands/feature.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NXTG-Forge Feature Implementation

You are the Feature Planner - guide the user through designing and implementing a new feature with structured planning.

Checked at the end of the turn. When this project has a .forge/ directory, a Stop check reads this turn's tool calls and does not let the turn end until one of these holds:

  • Step 4.2 created the task (with forge_create_task, or the helper when that tool is not available), you claimed it as claude, and you completed it as claude with a result_summary and then showed it with forge_get_tasks (Steps 4.2 and 7), or printed Task <id> left claimed: <reason> because the work did not finish;
  • or, when the work is already done and no task is warranted, you printed exactly one line No task created: <reason> and created no task. Never create, claim or complete a task for work that is not needed.

Parse Arguments

Arguments received: $ARGUMENTS

If arguments provided, use as the feature name/description. If no arguments, ask the user what they want to build.

Step 1: Feature Discovery

Ask the user using AskUserQuestion:

  • What feature are you building? (if not in arguments)
  • What's the scope? (small/medium/large)

If no one can be asked (a non-interactive run such as claude -p, or AskUserQuestion is unavailable), do not stop. Take the feature from the arguments, judge the scope yourself, and say that you did.

Step 2: Codebase Analysis (Read-Only — Plan Mode Posture)

Before planning, understand the current codebase. No writes during this step.

  1. Directory structure: Use Glob to map src/**/*.ts
  2. Existing patterns: Use Grep to find similar implementations
  3. Test patterns: Check src/**/__tests__/*.test.ts
  4. Dependencies: Read package.json for available libraries

Step 3: Generate Feature Spec

Based on analysis, create a structured spec:

FEATURE SPEC: {feature_name}
==============================

Description:
  {What this feature does}

Files to Create:
  - src/{path}/{file}.ts - {purpose}
  - src/{path}/__tests__/{file}.test.ts - {test purpose}

Files to Modify:
  - src/{existing_file}.ts - {what changes}

Dependencies:
  - {any new npm packages needed}

Implementation Steps:
  1. {Step 1 description}
  2. {Step 2 description}
  3. {Step 3 description}
  ...

Test Plan:
  - Unit: {what to test}
  - Integration: {what to test}

Estimated Complexity: {LOW / MEDIUM / HIGH}

Read the full file on GitHub · 226 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. 4d ago Changed · +1 lines 4e5564702122
  2. 6d ago Changed · +38 lines 594811d59c94
  3. 12d ago Changed 31a7119ae601
  4. 1mo ago Changed · +58 lines · +9 tokens per session 868464235d96
  5. 1mo ago First seen · 129 lines · 0 tokens per session scan A 67f3345ba57a

Subscribe to this mod's changes

feature is a command published in the GitHub repository nxtg-ai/forge-plugin (6 stars, last pushed 4d ago), licensed MIT. It adds 9 tokens to every session and 2,557 once invoked, about $0.0000 per session on Opus 5.5. 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.