rapp-pipeline-guide

rapp-pipeline-guide is an agent for Claude Code from microsoft/aibast-agents-library. It costs 0 tokens per session (4,758 once invoked), scanned A, original, MIT.

A guide for taking a project through RAPP, a 14-step process for discovering, building, checking, deploying, and maintaining AI agents. It can also turn a transcript into agent code and a demo.

In plain words
What is it for?
Validating requirements, generating Python agents, creating demos from transcripts, tracking progress, and preparing agents for Azure deployment.
Why use it?
It gives teams a structured path from requirements to deployment, with checkpoints that help catch problems and limit uncontrolled scope.

Agent for Claude Code ✓ vendor

Written for Claude Code: installed under .claude/.

Good fit Validating requirements, generating Python agents, creating demos from transcripts, tracking progress, and preparing agents for Azure deployment.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/microsoft/aibast-agents-library/rapp-pipeline-guide
About the project

AIBAST Agents Library is a collection of industry-focused AI agent templates accompanied by a local server that connects agents to GitHub Copilot for language-model inference. It helps developers create and run tool-using agents and isolated project environments, with an optional cloud-backed path for persistent memory. The catalogue entries provide the repository's agents, skills, commands, hooks, and instructions.

microsoft/aibast-agents-library · 8 stars · on GitHub

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.

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-pipeline-guide

README.md
[![agentmods](https://agentmods.dev/badge/agents/microsoft/aibast-agents-library/rapp-pipeline-guide/github.svg)](https://agentmods.dev/agents/microsoft/aibast-agents-library/rapp-pipeline-guide)
Your own site
<a href="https://agentmods.dev/agents/microsoft/aibast-agents-library/rapp-pipeline-guide"><img src="https://agentmods.dev/badge/agents/microsoft/aibast-agents-library/rapp-pipeline-guide/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.

agentmods 80×15 button for rapp-pipeline-guide

Your own site · 80×15
<a href="https://agentmods.dev/agents/microsoft/aibast-agents-library/rapp-pipeline-guide"><img src="https://agentmods.dev/badge/agents/microsoft/aibast-agents-library/rapp-pipeline-guide.svg" alt="Reviewed on agentmods" width="80" 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 4,758 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.04758
Opus 5.5 $0.00000 $0.01903
Sonnet 5.5 $0.00000 $0.00952
Haiku 4.5 $0.00000 $0.00476

Measured 2mo ago against content hash 803176afc69d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rapp-pipeline-guide scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST "YOUR_FUNCTION_URL?code=YOUR_KEY" \
community_rapp/project/.claude/agents/rapp-pipeline-guide.md · 597 lines

How it starts

The opening of the file, as written. The whole thing — 597 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RAPP Pipeline Guide Agent

You are the RAPP Pipeline Guide, an expert assistant helping users navigate the complete 14-step RAPP (Rapid AI Agent Production Pipeline) process from initial discovery to production deployment and maintenance.

Your Mission

Guide users through building AI agents for business applications using a structured, quality-gated process. You ensure projects succeed by:

  • Validating requirements before building
  • Generating production-ready code
  • Enforcing quality gates at each stage
  • Tracking progress persistently
  • Preventing scope creep

When a user provides a transcript, USE THIS IMMEDIATELY:

This is the fastest way to go from discovery call to working agent. One API call generates:

  • Complete Python agent code (BasicAgent pattern)
  • Demo JSON for ScriptedDemoAgent
  • Both auto-deployed to Azure File Storage

How to Process a Transcript

Step 1: User provides transcript -> Step 2: Call transcript_to_agent -> Step 3: Agent + Demo ready to use

Use the RAPP agent with transcript_to_agent action:

Use RAPP agent with:
  action="transcript_to_agent"
  transcript="[PASTE THE FULL TRANSCRIPT]"
  customer_name="[CUSTOMER NAME]"
  agent_priority="[OPTIONAL: contract, chargeback, analytics, etc.]"
  deploy_to_storage=true

Example with a customer transcript:

Use RAPP with action=transcript_to_agent, customer_name="Acme Corp",
agent_priority="contract", deploy_to_storage=true, and this transcript:

[0:32] Tracy Yang: Hi, Christian. Happy New Year...
[Paste full transcript here]

What happens:

  1. Transcript is analyzed to identify the best agent opportunity
  2. Complete agent code is generated following BasicAgent pattern
  3. Demo JSON is generated for ScriptedDemoAgent
  4. HTML tester page is generated (test both real agent and demo)
  5. All files saved to rapp_projects/{project_id}/outputs/:
    rapp_projects/{project_id}/outputs/
    ├── {agent_id}_agent.py      # Agent code
    ├── {agent_id}_demo.json     # Demo JSON
    ├── agent_tester.html        # HTML tester (Real Agent + Demo Mode tabs)
    └── result.json              # Metadata
    
  6. Also deployed to main agents/ and demos/ folders
  7. Agent is ready to use after function app restart

Read the full file on GitHub · 597 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. 2mo ago First seen · 597 lines · 0 tokens per session scan A 803176afc69d

Subscribe to this mod's changes

rapp-pipeline-guide is an agent published in the GitHub repository microsoft/aibast-agents-library (8 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,758 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

rapp-pipeline-guide compared with agents from other repositories

rapp-pipeline-guide next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
rapp-pipeline-guidemicrosoft/aibast-agents-libraryAgent8yesterdayMITA0Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code
code-revieweranthropics/claude-cookbooksAgent54k2d agoMITA52Claude Code
AVM Owner Triagegithub/awesome-copilotAgent41kyesterdayMITA61Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilotAgent41kyesterdayMITA11Claude Code
WinForms Expertgithub/awesome-copilotAgent41kyesterdayMITA19Claude Code