define

An interactive project setup command for Ralph Loop, a workflow that guides coding agents through planned work using instruction and specification files.

In plain words
What is it for?
Use it to interview the user, detect the project's current planning state, and create or update PROMPT.md, AGENT.md, specifications, and a fix plan after showing the proposed changes.
Why use it?
It removes the need to create and maintain several Markdown control files by hand.

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/define
Clone the repo
git clone --depth 1 https://github.com/develo-pera/ralph-kit
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,208 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 $0.00044 $0.01208
Opus 5 $0.00022 $0.00604
Sonnet 5 $0.00009 $0.00242
Haiku 4.5 $0.00004 $0.00121

Measured 2d ago against content hash 66a9280f5227, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

define 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.

commands/define.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ralph-kit:define

You are running the Ralph-Kit project-definition interview. The target project is the user's current working directory; all writes go to ./​.ralph/.

Step 1 — Detect state

Read these files if present:

  • .ralph/PROMPT.md
  • .ralph/fix_plan.md
  • .ralph/AGENT.md
  • .ralph/specs/ (list files)
  • package.json, pyproject.toml, Cargo.toml, go.mod (for stack autodetection)

Classify the project state:

Signal Classification
fix_plan.md begins with Status: BLOCKED or is empty EMPTY
PROMPT.md is default-looking + specs/ empty LIGHT
Rich PROMPT.md + ≥1 spec file RICH

State the classification in one sentence, then use AskUserQuestion to offer modes:

  • EMPTY → only Create (no other choice needed — proceed).
  • LIGHT → Update full, Supplement missing, Cancel.
  • RICH → Supplement missing, Add feature, Revise single file, Cancel.

Step 2 — Interview (create / update)

Use AskUserQuestion for branching answers and plain chat messages for free-text. Ask one stage at a time.

Stage A — Identity

  1. Project name (confirm against .ralphrc PROJECT_NAME if present).
  2. One-sentence purpose.
  3. Target user (who will use this thing?).
  4. Success criteria — free text, "we'll know this is done when…".

Stage B — Scope & stack

  1. Language / framework — offer detected stack as recommended option.
  2. Deployment target (local CLI, web app, Docker, serverless, library, other).
  3. Must-have features — free text, one per line, ≥1.
  4. Nice-to-have features — free text, optional.

Stage C — Features (loop per must-have) For each must-have feature ask (as one AskUserQuestion with free-text options, OR as three chat questions):

  1. What does it do? (1–2 sentences.)
  2. Inputs / outputs — what goes in, what comes out.
  3. Acceptance — how will we know it works? (testable bullet list.)

Stage D — Build commands Offer detected install / run / test commands as the recommended answer. User confirms or edits.

Read the full file on GitHub · 105 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 · 105 lines · 44 tokens per session scan A 66a9280f5227

Subscribe to this mod's changes

define is a command published in the GitHub repository develo-pera/ralph-kit (5 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 1,208 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.