feature

A tool for creating or revising one product-feature file with a user story, at least three Given/When/Then acceptance tests, and a classification as either innovation or implementation.

In plain words
What is it for?
Use it to add a feature to Product/Features/ or improve an existing one with its user, benefit, dependencies, priority, status, and testable requirements.
Why use it?
It gives each feature a consistent description and concrete conditions for deciding whether it works. Given/When/Then is a plain format for describing starting conditions, an action, and the expected result.

Skill for Claude CodeCodex

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 skills/inscico/i-framework/feature
Any agent
npx skills add InSciCo/i-framework --skill feature
Clone the repo
git clone --depth 1 https://github.com/InSciCo/i-framework

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 884 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 $0.00057 $0.00884
Opus 5 $0.00028 $0.00442
Sonnet 5 $0.00011 $0.00177
Haiku 4.5 $0.00006 $0.00088

Measured 2d ago against content hash 1c5cfaeee74c, 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 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.

.claude/skills/feature/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/feature — author one feature file (the atom)

You produce or revise exactly one file in Product/Features/ that conforms to the feature schema. Be strict: a feature is not done until it has a complete user story, at least three testable acceptance criteria, and a classification with a rationale.

Procedure

  1. Locate the product root. Find Product/Features/ from the current directory. If Product/ doesn't exist, tell the user to run /intent first (or offer to create the folder if they just want to draft features directly).

  2. New or revise?

    • Revise: if the user names an existing feature (by id or title), read that file and edit in place — keep the id stable.
    • New: scan Features/F*.md, find the highest F<NNN>, assign the next id. Filename = F<NNN>-<kebab-slug>.md.
  3. Gather the content. You need: title, persona, capability, benefit (the user story); ≥3 acceptance criteria; classification; rationale; priority; status; and any dependencies on other features (depends_on). If the caller (e.g. /innovate) supplied these, use them. If invoked standalone with gaps, ask the user one focused question at a time (use AskUserQuestion for the classification fork). Do not invent a user story from nothing — ask.

  4. Classify (mirror /classify's rubric):

    • Apply the decision test: "If a competitor shipped this exact feature tomorrow, would we lose our edge?"innovation. "Would every competitor's product have this too?"implementation.
    • Set innovation_weight: implementation → 0; innovation → 1–100 by how much of the moat it carries.
    • For innovation features, set contributes_to to a UVP id from Product/innovation.md (read it if present). If you can't point to a UVP element, that's a signal the feature may actually be implementation — challenge it.
    • Write a one-sentence classification_rationale.
  5. Write the file using the schema below (canonical copy lives at the plugin's templates/feature.md). Validate before finishing:

    • User story has all three clauses (As a… / I want… / so that…).
    • ≥3 acceptance criteria, each observable and testable (Given/When/Then, or a plain checkbox where GWT is awkward).
    • classification + innovation_weight + classification_rationale all present and mutually consistent (implementation ⇒ weight 0).

Read the full file on GitHub · 62 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 · 62 lines · 57 tokens per session scan A 1c5cfaeee74c

Subscribe to this mod's changes

feature is a skill published in the GitHub repository InSciCo/i-framework (4 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 884 once invoked, about $0.0003 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.