What is features:init?

A command that creates a standard folder for feature documentation and fills it with starter templates. Feature documentation describes what the software should do and how its parts relate.

Use it to start feature documentation, create the feature index and template files, and prepare the project for later analysis or manual feature additions.

It gives a new project a consistent place and format for recording technical requirements before you begin adding or analysing features.

features:init — Command by ruslan-korneev

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/ruslan-korneev/claude-plugins/features-init

Clone the repo

git clone --depth 1 https://github.com/ruslan-korneev/claude-plugins

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 586 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.

Model	Per session	Once invoked
Fable 5	$0.00012	$0.00586
Opus 5	$0.00006	$0.00293
Sonnet 5	$0.00002	$0.00117
Haiku 4.5	$0.00001	$0.00059

Measured 2d ago against content hash f042912d0dfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

features:init 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.

plugins/tech-lead/commands/features-init.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.

Command /feature-list:init

Initialize the feature documentation directory structure.

Instructions

Step 1: Determine Target Path

Use the provided path argument or default to docs/technical-requirements/features.

Step 2: Check for Existing Directory

Use Glob to check if the directory already exists:

{path}/*.md

If files exist, inform the user:

⚠️ Feature directory already exists at `{path}`.

Found {count} feature files:
- {file1}
- {file2}
...

Use `/feature-list:analyze` to update from codebase or `/feature-list:add` to add new features.

Step 3: Create Directory Structure

If the directory doesn't exist, create it:

mkdir -p {path}

Step 4: Copy Templates

Read templates from the plugin and write them to the target directory:

Read ${CLAUDE_PLUGIN_ROOT}/templates/00-template.md
Write to {path}/00-template.md
Read ${CLAUDE_PLUGIN_ROOT}/templates/readme-template.md
Write to {path}/README.md

Step 5: Confirm Completion

✅ Feature directory initialized at `{path}`

Created files:
- `{path}/README.md` — Feature index with dependency graph
- `{path}/00-template.md` — Template for new features

## Next Steps

1. **Analyze existing codebase**: `/feature-list:analyze`
2. **Design new features**: `/feature-list:design`
3. **Add a feature manually**: `/feature-list:add core user-management`

Response Format

## Feature Directory Initialized

📁 Created `{path}/`

### Files Created

| File | Purpose |
|------|---------|
| `README.md` | Feature index with dependency graph |
| `00-template.md` | Template for new features |

### Next Steps

- Run `/feature-list:analyze` to extract features from existing code
- Run `/feature-list:design` for interactive feature design
- Run `/feature-list:add <phase> <name>` to add a single feature

Edge Cases

Directory Exists but Empty

If the directory exists but has no .md files, proceed with initialization.

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.

2d ago First seen · 112 lines · 12 tokens per session scan A f042912d0dfd

Subscribe to this mod's changes

features:init is a command published in the GitHub repository ruslan-korneev/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 586 once invoked, about $0.0001 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 2026-08-31.

Backend and APIs Languages Writing and docs claude-code claude-code-plugin claude-code-plugins-marketplace python

features:init