rapp-step

rapp-step is a command for Claude Code from microsoft/aibast-agents-library. It costs 0 tokens per session (1,086 once invoked), scanned A, original, MIT.

A step-by-step guide for the 14-stage RAPP delivery process. RAPP is a workflow that turns a customer conversation into a validated proposal and later delivery steps.

In plain words
What is it for?
Use it to prepare or process discovery calls, validate transcripts, create an MVP proposal, prioritize features, and run the relevant quality gates.
Why use it?
It explains what information and action are needed at a chosen stage, reducing confusion about the next task and the expected result.

Command for Claude Code

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/microsoft/aibast-agents-library/rapp-step
Clone the repo
git clone --depth 1 https://github.com/microsoft/aibast-agents-library

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.

agentmods badge for rapp-step

README.md
[![agentmods](https://agentmods.dev/badge/commands/microsoft/aibast-agents-library/rapp-step.svg)](https://agentmods.dev/commands/microsoft/aibast-agents-library/rapp-step)
Your own site
<a href="https://agentmods.dev/commands/microsoft/aibast-agents-library/rapp-step"><img src="https://agentmods.dev/badge/commands/microsoft/aibast-agents-library/rapp-step.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 1,086 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 $0.01086
Opus 5 $0.00000 $0.00543
Sonnet 5 $0.00000 $0.00217
Haiku 4.5 $0.00000 $0.00109

Measured 3d ago against content hash 7ef94f0bcffb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rapp-step 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 3d 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.

rapp_ai/.claude/commands/rapp-step.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RAPP Step Guide

Guide the user through a specific RAPP pipeline step. The argument should be the step number (1-14).

All operations use the single RAPP agent with different actions.

Step Details

Based on the step number provided ($ARGUMENTS), give detailed guidance:

Step 1: Discovery Call

What to do: Prepare for and process a discovery call RAPP Actions:

  • prepare_discovery_call - Generate call prep guide
  • process_transcript - Process transcript after call Inputs needed: customer_name, industry (for prep); customer_name, transcript (for processing) Outputs: Discovery guide, extracted problem statements, data sources, stakeholders, success criteria

Step 2: QG1 - Transcript Validation

What to do: Validate discovery data completeness RAPP Action: execute_quality_gate with gate="QG1" Inputs needed: customer_name, project_name, input_data (discovery data) Outputs: PASS/CLARIFY/FAIL decision with scores

Step 3: MVP Poke Document

What to do: Generate customer proposal document RAPP Actions:

  • generate_mvp_poke - Quick MVP proposal
  • generate_full_mvp_document - Complete customer-ready document
  • prioritize_features - Feature prioritization
  • define_scope - Scope boundaries Inputs needed: customer_name, project_name, problem_statement, discovery_data Outputs: Full MVP document with features, timeline, risks

Step 4: QG2 - Customer Validation

What to do: Get customer sign-off, LOCK SCOPE RAPP Action: execute_quality_gate with gate="QG2" Inputs needed: input_data (MVP document + customer response) Outputs: PROCEED/REVISE/HOLD decision, scope lock confirmation

Step 5: Generate Agent Code

What to do: Create Python agent following BasicAgent pattern RAPP Actions:

  • generate_agent_code - Full agent code
  • generate_agent_metadata - Metadata schema only Inputs needed: agent_name, agent_description, features, data_sources Outputs: Complete Python agent code

Read the full file on GitHub · 108 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. 3d ago First seen · 108 lines · 0 tokens per session scan A 7ef94f0bcffb

Subscribe to this mod's changes

rapp-step is a command published in the GitHub repository microsoft/aibast-agents-library (7 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,086 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.