add-feature

add-feature is a command for coding agents from develo-pera/ralph-kit. It costs 31 tokens per session (398 once invoked), scanned A, original, MIT.

Um comando que transforma uma nova funcionalidade de um projeto Ralph em uma especificação e tarefas para o plano de trabalho.

In plain words
What is it for?
Serve para documentar uma funcionalidade em `.ralph/specs` e acrescentar de duas a quatro tarefas relacionadas ao `fix_plan.md`, com prioridade escolhida.
Why use it?
Organiza a ideia em descrição, entradas, saídas e critérios verificáveis antes de incluí-la no plano. Mostra as alterações e pede confirmação antes de gravar os arquivos.

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/develo-pera/ralph-kit/add-feature
Clone the repo
git clone --depth 1 https://github.com/develo-pera/ralph-kit

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 add-feature

README.md
[![agentmods](https://agentmods.dev/badge/commands/develo-pera/ralph-kit/add-feature.svg)](https://agentmods.dev/commands/develo-pera/ralph-kit/add-feature)
Your own site
<a href="https://agentmods.dev/commands/develo-pera/ralph-kit/add-feature"><img src="https://agentmods.dev/badge/commands/develo-pera/ralph-kit/add-feature.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 398 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 $0.00031 $0.00398
Opus 5 $0.00015 $0.00199
Sonnet 5 $0.00006 $0.00080
Haiku 4.5 $0.00003 $0.00040

Measured 4d ago against content hash 21966ba91011, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-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/add-feature.md · 41 lines

What it actually says

/ralph-kit:add-feature

Add a single feature to the current Ralph project (./​.ralph/).

Step 1 — Prerequisites

Read .ralph/fix_plan.md and .ralph/PROMPT.md. If either is missing or fix_plan.md starts with Status: BLOCKED, stop and tell the user to run /ralph-kit:define first.

Step 2 — Feature intake

If the user passed a feature name as argument, use it as the default. Otherwise ask for the name. Then ask the three mini-spec questions:

  1. What does it do? (1–2 sentences.)
  2. Inputs / outputs.
  3. Acceptance criteria (testable bullets).

Then ask the priority with AskUserQuestion: High, Medium, Low.

Step 3 — Draft tasks

Expand the feature into 2–4 tasks sized for one Ralph loop each. Show the draft in chat.

Step 4 — Diff preview + write

  1. Show the new .ralph/specs/<slug>.md content.
  2. Show the appended-to fix_plan.md section as a diff.
  3. Ask with AskUserQuestion: Apply, Edit, Cancel.
  4. On Apply, write the spec file and rewrite fix_plan.md with the appended tasks.

Guardrails

  • Slug = kebab-case of feature name; if specs/<slug>.md exists, append suffix -2, -3, etc.
  • Never modify existing tasks; only append.
  • Never write outside .ralph/.
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 · 41 lines · 31 tokens per session scan A 21966ba91011

Subscribe to this mod's changes

add-feature is a command published in the GitHub repository develo-pera/ralph-kit (5 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 398 once invoked, about $0.0002 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.