neo: Command for Claude Code

.claude/commands/feature-autonomous.md

feature-autonomous is a command for Claude Code from Parslee-ai/neo. It costs 22 tokens per session (1,949 once invoked), scanned A, original, Apache-2.0.

An automated workflow for researching, planning, and implementing a software feature.

In plain words
What is it for?
Use it to turn a feature description into a researched implementation plan and validated code changes.
Why use it?
It gathers codebase context and defines tests and acceptance criteria before implementation, reducing missed requirements.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the SlashCommand tool.

This is Parslee-ai/neo's own configuration. It tells Claude Code how to work on neo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything neo configures →

Part of the neo plugin — 9 skills, 18 commands, 1 agent, 1 hook shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to Parslee-ai/neo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Parslee-ai/neo/main/.claude/commands/feature-autonomous.md
Clone the repo
git clone --depth 1 https://github.com/Parslee-ai/neo

Made for: Claude Code.

Or install neo, the plugin that ships this one along with the rest of its 9 skills, 18 commands, 1 agent, 1 hook.

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-autonomous

README.md
[![agentmods](https://agentmods.dev/badge/commands/parslee-ai/neo/feature-autonomous.svg)](https://agentmods.dev/commands/parslee-ai/neo/feature-autonomous)
Your own site
<a href="https://agentmods.dev/commands/parslee-ai/neo/feature-autonomous"><img src="https://agentmods.dev/badge/commands/parslee-ai/neo/feature-autonomous.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,949 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 $0.00022 $0.01949
Opus 5 $0.00011 $0.00975
Sonnet 5 $0.00004 $0.00390
Haiku 4.5 $0.00002 $0.00195

Measured 8d ago against content hash 09cc4cc1a694, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

feature-autonomous 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 8d 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/feature-autonomous.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Feature Planning & Implementation

Generate a feature implementation plan using multi-agent research (Phase 0 from quick-ship-neo), then implement with full validation loop.

Instructions

  • You're autonomously planning and implementing a feature using Phase 0 research
  • Phase 0: Use 3 agents to research and generate O1-O4 implementation options
  • CRITICAL: Phase 0 MUST output explicit Test Specification
  • After planning, automatically proceed to /implement with the generated plan

Feature

$ARGUMENTS

Phase 0: PreflightExplain

Step 0.1: Parse Feature

  • Extract feature description from $ARGUMENTS
  • Classify type (new functionality, enhancement, integration, infrastructure)
  • Define acceptance criteria (feature is complete when...)
  • Identify user story components (who, what, why)

Step 0.2: Codebase Research

  • INVOKE Task tool:
    • subagent_type: "codebase-researcher"
    • description: "Research codebase for feature context"
    • prompt: "Research the codebase for feature: {feature_description}. Identify: (1) Existing patterns and conventions to follow, (2) Files that will need modification, (3) Similar features already implemented, (4) Architecture constraints and opportunities, (5) Dependencies and integration points. Provide structured report with file paths, line numbers, and code patterns."

Step 0.3: Feature Analysis

  • INVOKE Task tool:
    • subagent_type: "debug-detective"
    • description: "Deep feature analysis"
    • prompt: "Analyze feature requirements: {feature_description}. Investigate: (1) Core functionality needed, (2) Edge cases and error scenarios, (3) User experience considerations, (4) Performance implications, (5) Security considerations, (6) Complexity assessment. Provide comprehensive analysis."

Step 0.4: Generate Implementation Options

  • INVOKE Task tool:
    • subagent_type: "linus-kernel-planner"
    • description: "Generate O1-O4 implementation options"
    • prompt: "Create feature implementation plan for: {feature_description}. Generate exactly 4 options (O1-O4), each with: approach overview, files to create/modify, complexity assessment (LOC, risk level), architectural implications, risks and tradeoffs. Include: (1) Feature Assessment, (2) Rejected Approaches (over-engineered solutions), (3) Four Implementation Options with tradeoffs, (4) Recommended Solution (simplest that meets requirements), (5) What NOT to Do (avoid complexity). Follow existing patterns. Prefer simple, extensible solutions."

Read the full file on GitHub · 234 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. 8d ago First seen · 234 lines · 22 tokens per session scan A 09cc4cc1a694

Subscribe to this mod's changes

feature-autonomous is a command published in the GitHub repository Parslee-ai/neo (16 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 1,949 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 2026-08-30.