feature

A structured workflow for developing a software feature through research, design, implementation, and validation phases. It requires approval between phases.

In plain words
What is it for?
Clarifying feature requests, researching existing solutions, creating worktrees, implementing changes, and running build, test, and end-to-end checks.
Why use it?
It provides checkpoints for decisions and testing, reducing the chance of implementing the wrong feature or skipping important verification.

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/qwickapps/ai-sdlc-workflows/feature
Clone the repo
git clone --depth 1 https://github.com/qwickapps/ai-sdlc-workflows

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,703 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00010 $0.02703
Opus 5 $0.00005 $0.01352
Sonnet 5 $0.00002 $0.00541
Haiku 4.5 $0.00001 $0.00270

Measured 2d ago against content hash 7c855e2e3512, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **For JIRA tickets**: Use JIRA CLI `jira issue attach <ticket-key> <frd-path>` or REST API `curl -X POST -H "X-Atlassian-Token: no-check" -F "file=@<frd-path>" <jira-url>/rest/api/2/issue/<ticket-key>/attachments`
claude/.claude/commands/feature.md · 341 lines

How it starts

The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Development Workflow

You are now in Feature Development Mode. Follow this SDLC workflow strictly.

<critical_rules>

CRITICAL RULES

  1. NEVER skip phases - each phase requires user approval before proceeding
  2. NEVER auto-commit - always wait for explicit user approval
  3. NEVER add legacy support unless explicitly requested
  4. REUSE FIRST - always check existing solutions (see RESEARCH-DEPTH.md)
  5. No attributions in commit messages
  6. When blocked - STOP and discuss (see COMMUNICATION-PROTOCOL.md)
  7. Validate thoroughly - build, test, E2E (see VALIDATION-GATES.md)
  8. Use worktree script - NEVER use git commands directly (see WORKTREE-ENFORCEMENT.md) </critical_rules>

<interactive_setup>

Interactive Setup

Check if $ARGUMENTS is provided.

If $ARGUMENTS is empty or unclear, ask: "What feature would you like to implement? Please provide:

  • A brief description of the feature
  • Issue/ticket number (GitHub issue, JIRA ticket, etc.)
  • Or context about the problem being solved"

Extract and store the issue/ticket number from the response for:

  • Branch naming (feature/ISSUE-123)
  • Document attachment
  • Commit messages

Wait for response before proceeding. </interactive_setup>

Workflow Phases

<phase_1_requirements>

PHASE 1: Requirements (Product Manager)

Adopt the product-manager agent persona. Your job is to:

  1. Understand the request - Ask clarifying questions about:

    • What problem does this solve?
    • Who are the users/stakeholders?
    • What are the success criteria?
    • What are the constraints (time, technical, business)?
    • Are there existing solutions to reuse?
  2. Document requirements - Create a Feature Request Document:

    • Save to: .claude/engineering/frd/FRD-<id>-<short-name>.md
    • Use template from .claude/templates/FRD.md
  3. Attach FRD to issue/ticket (if issue number provided):

    • For GitHub issues: Use gh issue comment <issue-number> --body-file <frd-path> or gh issue edit <issue-number> --add-attachment <frd-path> (if supported)
    • For JIRA tickets: Use JIRA CLI jira issue attach <ticket-key> <frd-path> or REST API curl -X POST -H "X-Atlassian-Token: no-check" -F "file=@<frd-path>" <jira-url>/rest/api/2/issue/<ticket-key>/attachments
    • If attachment fails or not applicable: Inform user to attach manually

Read the full file on GitHub · 341 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 · 341 lines · 10 tokens per session scan A 7c855e2e3512

Subscribe to this mod's changes

feature is a command published in the GitHub repository qwickapps/ai-sdlc-workflows (2 stars, last pushed 5mo ago), licensed MIT. It adds 10 tokens to every session and 2,703 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.