create-features

A command that turns an implementation plan into a structured set of feature documents.

In plain words
What is it for?
Use it to create feature folders, an overview table, and numbered files describing each planned feature.
Why use it?
It gives a large plan a consistent folder structure, source copy, overview, status tracking, and dependency order.

Command 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 commands/polarcoding85/convex-agent-skillz/create-features
Clone the repo
git clone --depth 1 https://github.com/PolarCoding85/convex-agent-skillz

Made for: Claude Code.

Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 442 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 $0.00006 $0.00442
Opus 5 $0.00003 $0.00221
Sonnet 5 $0.00001 $0.00088
Haiku 4.5 $0.00001 $0.00044

Measured 2d ago against content hash eeee1880be7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-features 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.

.claude/commands/create-features.md · 86 lines

What it actually says

Convert the implementation plan above into a structured feature breakdown. Follow these steps precisely:

1. Directory Setup

  • Create docs/features/ if it doesn't exist
  • Create a sub-folder using kebab-case based on the plan name (e.g., docs/features/user-authentication/)

2. Copy Source Plan

  • Save the original implementation plan as _source-plan.md in the sub-folder

3. Create Overview File

Create 00-overview.md with this structure:

# [Feature Set Name]

## Summary

[Brief description of what this implementation achieves]

## Features

| #   | Feature | File                 | Status         | Dependencies |
| --- | ------- | -------------------- | -------------- | ------------ |
| 1   | [Name]  | `01-feature-name.md` | ⬜ Not Started | None         |
| 2   | [Name]  | `02-feature-name.md` | ⬜ Not Started | #1           |

## Status Legend

- ⬜ Not Started
- 🟡 In Progress
- ✅ Complete
- ⛔ Blocked

## Implementation Order

[Recommended sequence based on dependencies]

4. Create Individual Feature Files

For each feature, create a numbered file (e.g., 01-feature-name.md) with:

# Feature: [Name]

## Overview

[What this feature does and why]

## Dependencies

- **Requires:** [List prerequisite features by number, or "None"]
- **Blocks:** [List features that depend on this one]

## Acceptance Criteria

- [ ] [Criterion 1]
- [ ] [Criterion 2]

## Technical Details

[Implementation specifics from the plan]

## Files to Create/Modify

- `path/to/file.ts` - [Purpose]

## Notes

[Any additional context or considerations]

Guidelines

  • Extract atomic, independently testable features
  • Identify implicit dependencies between features
  • Preserve all technical details from the source plan
  • Use clear, action-oriented feature names
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 · 86 lines · 6 tokens per session scan A eeee1880be7d

Subscribe to this mod's changes

create-features is a command published in the GitHub repository PolarCoding85/convex-agent-skillz (17 stars, last pushed 6mo ago), licensed MIT. It adds 6 tokens to every session and 442 once invoked, about $0.0000 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.