feature

feature is a command for coding agents from aadivar/shiplog. It costs 0 tokens per session (479 once invoked), scanned A, original, MIT.

A command for creating a feature document and adding the feature to a product requirements document. A product requirements document lists the planned features of a project.

In plain words
What is it for?
Use it to assign the next feature ID, create a file from the project template, and add the feature to the current sprint’s requirements.
Why use it?
It keeps the new feature’s detailed description and project-wide feature list in sync.

Command

Part of the shiplog plugin — 1 skill, 8 commands, 4 agents, 1 hook shipped together

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/aadivar/shiplog/feature
Clone the repo
git clone --depth 1 https://github.com/aadivar/shiplog

Or install shiplog, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 4 agents, 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

README.md
[![agentmods](https://agentmods.dev/badge/commands/aadivar/shiplog/feature.svg)](https://agentmods.dev/commands/aadivar/shiplog/feature)
Your own site
<a href="https://agentmods.dev/commands/aadivar/shiplog/feature"><img src="https://agentmods.dev/badge/commands/aadivar/shiplog/feature.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 479 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 $0.00000 $0.00479
Opus 5 $0.00000 $0.00239
Sonnet 5 $0.00000 $0.00096
Haiku 4.5 $0.00000 $0.00048

Measured 4d ago against content hash 9135674c329d, 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 4d 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.

commands/feature.md · 55 lines

What it actually says

/shiplog feature

Create a new feature file and add it to the PRD.

Trigger

User runs /shiplog feature "<name>" or /shiplog feature

Behavior

Step 1: Validate setup

Check that .shiplog/config.json exists and docs/PRD.md exists. If not:

"Shiplog is not initialized. Run /shiplog init first."

Step 2: Get feature name

  • If the user provided a name as an argument (e.g., /shiplog feature "user auth"), use that
  • If no name was provided, ask: "What's the feature name?"

Step 3: Assign feature ID

Read docs/PRD.md and find the highest existing feature ID (e.g., F003). Assign the next sequential ID (e.g., F004).

Step 4: Get current sprint

Read docs/PROGRESS.md to determine the current sprint number.

Step 5: Create feature file

Read the template from templates/feature.md.hbs and create the feature file:

  • Path: docs/features/{featureId}-{kebab-case-name}.md
  • Replace template variables:
    • {{featureId}} — e.g., F004
    • {{featureName}} — The feature name provided by user
    • {{sprint}} — Current sprint number
    • {{date}} — Today's date (YYYY-MM-DD)

Step 6: Add to PRD

Append a new row to the feature table in docs/PRD.md:

| {ID} | {name} | not-started | {sprint} | |

Step 7: Confirm

Created feature {ID} — {name}
  File: docs/features/{ID}-{kebab-name}.md
  Sprint: {N}
  Status: not-started

  Edit the feature file to add description and acceptance criteria.

Rules

  • Feature IDs are always sequential (F001, F002, F003...)
  • Feature file names use kebab-case (F004-user-authentication.md)
  • Never overwrite an existing feature file
  • If a feature with the same name already exists, warn the user
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. 4d ago First seen · 55 lines · 0 tokens per session scan A 9135674c329d

Subscribe to this mod's changes

feature is a command published in the GitHub repository aadivar/shiplog (3 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 479 tokens. 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.

Related

Other commands, from other repositories