A feature-planning process that creates a feature record in docs/features/ before code is written, linking the work to product requirements and affected architecture or data documents.

Use it for substantial features that fulfil product requirements or touch multiple layers; small fixes, copy changes, and style adjustments do not need this record.

It clarifies the agreement and scope for work that spans several parts of a project or will take more than one session.

How polmarza/project-template configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to polmarza/project-template. 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/polmarza/project-template/main/.claude/skills/feature/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/polmarza/project-template

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/polmarza/project-template/feature/github.svg)](https://agentmods.dev/skills/polmarza/project-template/feature)

Your own site

<a href="https://agentmods.dev/skills/polmarza/project-template/feature"><img src="https://agentmods.dev/badge/skills/polmarza/project-template/feature/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/polmarza/project-template/feature"><img src="https://agentmods.dev/badge/skills/polmarza/project-template/feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,140 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.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.01140
Opus 5.5	$0.00028	$0.00456
Sonnet 5.5	$0.00014	$0.00228
Haiku 4.5	$0.00007	$0.00114

Measured 14d ago against content hash d2cfe5f895b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 14d 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 · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crea la ficha de una feature nueva en docs/features/, siguiendo el formato de docs/features/README.md.

Esto se hace antes de escribir código, no después. La ficha es el acuerdo previo; si ya hay código escrito, lo que toca es una entrada de changelog, no una ficha retroactiva.

1. Comprueba que hace falta

Una ficha se justifica si el trabajo cierra requisitos del PRD, toca varias capas o va a durar más de una sesión. Para un arreglo puntual o un cambio de copy, dilo y no la crees: basta el changelog al terminar.

2. Reúne el contexto

Lee docs/prd.md para localizar qué requisitos (M-01, S-02…) cierra esta feature. Si el trabajo no se corresponde con ningún requisito del PRD, hay dos posibilidades y conviene preguntarlas antes de seguir:

Es alcance nuevo → hay que añadirlo al PRD primero, con su ID y su criterio de aceptación.
Está fuera de alcance → va a mejoras/, no a docs/features/.

Lee también docs/architecture.md y docs/data-model.md si la feature toca estructura o datos.

3. Pregunta lo que no puedas deducir

Nombre de la feature (el archivo será kebab-case.md)
Qué debe poder hacer el usuario cuando esto exista
Qué queda explícitamente fuera

4. Escribe la ficha

Usa la plantilla de docs/features/README.md. Estado inicial: Acordada.

La tabla de cobertura se rellena entera, sin huecos. Por cada requisito, la tercera columna lleva una de tres cosas:

La ruta del test que lo validará.
revisión humana: <qué se mira>; <qué tiene que verse>, cuando se comprueba mejor con los ojos que con un test: cómo se ve una pantalla, cómo suena una conversación. Las dos partes, concretas: otra persona tiene que poder repetirla.
no verificable por interfaz: <razón concreta> seguido de cómo se comprobará entonces, para lo que no tiene interfaz que mirar (un índice, una variable de entorno).

Si no sabes cuál poner, pregunta — no lo dejes en blanco ni escribas un test que sabes que no vas a escribir. Y no uses la revisión humana para lo que un test cubriría bien: el test se repite solo en cada PR; la revisión depende de que alguien la haga.

Read the full file on GitHub · 90 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.

14d ago Changed · +38 lines d2cfe5f895b9
29d ago First seen · 52 lines · 71 tokens per session scan A ecf65d4e63a5

Subscribe to this mod's changes

feature is a skill published in the GitHub repository polmarza/project-template (89 stars, last pushed 15d ago), licensed MIT. It adds 71 tokens to every session and 1,140 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-08.

Planning Project management showcase

feature next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
featurepolmarza/project-template	Skill	89	15d ago	MIT	A	71	Claude Code
product-showcase-pageAffitor/affiliate-skills	Skill	767	18d ago	MIT	A	110	Claude Code
criador-de-portfolioricneves-ai/flowgrammers-skills	Skill	117	1mo ago	MIT	A	46	Claude Code, Codex
mk:showcasengocsangyem/MeowKit	Skill	15	5d ago	MIT	A	80	Claude Code
show-offvanducng/skills	Skill	8	yesterday	MIT	A	60	Claude Code
workspace-guidesamartined/mAIcelium	Skill	5	yesterday	none	A	53	Claude Code, Codex
rema-shoppingAlfredvc/rema1000-cli	Skill	13	6mo ago	MIT	A	43	Claude Code, Codex

project-template: Skill for Claude Code