feature

A guided workflow for building a software feature from its specification through a pull request, a proposed code change ready for review.

In plain words
What is it for?
It helps check dependencies, update sprint progress, clarify requirements, implement a feature, test it, and prepare the resulting change for review.
Why use it?
It organizes feature work into planned steps and can connect the work to sprint tasks or Jira issues, which track development work.

Command

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/alphaaiservice/cortex/feature
Clone the repo
git clone --depth 1 https://github.com/alphaaiservice/cortex
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,687 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 $0.00026 $0.01687
Opus 5 $0.00013 $0.00843
Sonnet 5 $0.00005 $0.00337
Haiku 4.5 $0.00003 $0.00169

Measured yesterday against content hash 87de1685752b, 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 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 yesterday.

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.

commands/feature.md · 190 lines

How it starts

The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guided Feature Development

Build feature: $ARGUMENTS


Phase 0: Sprint Plan Integration

Before starting, check if this feature maps to a sprint task:

0. If $ARGUMENTS looks like a Jira issue key (matches ^[A-Z][A-Z0-9]+-\d+$, e.g. "PROJ-123"):
   → The `jira-integration` skill handles it: read the issue via the Atlassian MCP
     server, use its summary + description + acceptance criteria as the feature spec,
     and transition the issue to "In Progress". Then continue the flow below.
   → If Jira isn't connected, fall back to treating $ARGUMENTS as a plain description.
1. Check if SPRINT_PLAN.md exists
2. If $ARGUMENTS references a task ID (e.g., "task 2.3", "sprint task 2.3", or just "2.3"):
   a. Read SPRINT_PLAN.md
   b. Find the matching task
   c. Verify its dependencies are completed (all blockedBy tasks are ✅)
   d. If blocked: "⚠️ Task 2.3 is blocked by task 2.1 (not yet completed). Build task 2.1 first?"
   e. If unblocked: Mark task as 🔄 (in progress) in SPRINT_PLAN.md
   f. Use the task's description as the feature specification
3. If $ARGUMENTS is a description (not a task ID):
   a. Search SPRINT_PLAN.md for a matching task by description similarity
   b. If found: "Found matching sprint task 2.3. Linking this feature to it."
   c. Mark as 🔄 in SPRINT_PLAN.md
4. If no SPRINT_PLAN.md exists: proceed normally without sprint tracking

Phase 1: Planning

SCOPE CHECK (CRITICAL): If the feature is too large (would touch 5+ files or take more than 2 hours), SPLIT it into micro-tasks first:

  • Each micro-task = ONE file or ONE logical unit (max 2 hours)
  • Present the split to the user: "This feature is large. I'll break it into X micro-tasks and build them one by one."
  • Build each micro-task with its own commit
  • This prevents context window exhaustion
  1. Understand the requirement — Parse the feature description (or sprint task spec)
  2. Explore existing code — Find related modules, patterns, and conventions
  3. Create a plan — Generate a step-by-step implementation plan:

Read the full file on GitHub · 190 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. yesterday First seen · 190 lines · 26 tokens per session scan A 87de1685752b

Subscribe to this mod's changes

feature is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 25d ago), licensed MIT. It adds 26 tokens to every session and 1,687 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.