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.
npx agentmods add commands/microsoft/aibast-agents-library/rappgit clone --depth 1 https://github.com/microsoft/aibast-agents-libraryWhat 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 | $0.00000 | $0.01153 |
| Opus 5 | $0.00000 | $0.00576 |
| Sonnet 5 | $0.00000 | $0.00231 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
rapp 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAPP Pipeline Assistant
You are now in RAPP Pipeline mode. Help the user build an AI agent from discovery to deployment using the unified RAPP agent.
RECOMMENDED: Automated Workflow
The easiest way to use RAPP is the auto_process action:
-
Create project folder in Azure File Storage:
rapp_projects/{project_id}/ inputs/ outputs/ -
Drop input files into the
inputs/folder:File Type Expected Names Discovery transcript transcript.txt,discovery_call.txt,meeting_notes.txtCustomer feedback customer_feedback.txt,validation.txt,approval.txtCode for review agent_code.py,*.pyDeployment metrics metrics.json,telemetry.json,usage.json -
Call the RAPP agent with
auto_process:{ "action": "auto_process", "project_id": "acme-inventory-2024", "customer_name": "Acme Corp", "project_name": "Inventory Optimizer" } -
Professional PDF reports are generated in
outputs/:discovery_report_YYYYMMDD.pdfqg1_report_YYYYMMDD.pdfmvp_report_YYYYMMDD.pdfexecutive_summary_report_YYYYMMDD.pdf- etc.
Quick Reference - Pipeline Steps & Actions
| Step | Name | RAPP Agent Action | Gate |
|---|---|---|---|
| 1 | Discovery Call | prepare_discovery_call, process_transcript |
- |
| 2 | Transcript Validation | execute_quality_gate (gate=QG1) |
QG1 |
| 3 | MVP Poke Document | generate_mvp_poke, generate_full_mvp_document |
- |
| 4 | Customer Validation | execute_quality_gate (gate=QG2) |
QG2 (SCOPE LOCK) |
| 5 | Generate Agent Code | generate_agent_code |
- |
| 6 | Code Quality Review | execute_quality_gate (gate=QG3), review_code |
QG3 |
| 7 | Deploy Prototype | generate_deployment_config |
- |
| 8 | Demo Review | execute_quality_gate (gate=QG4) |
QG4 |
| 9 | Create Video Demo | - | - |
| 10 | Final Demo Review | execute_quality_gate (gate=QG5) |
QG5 |
| 11 | Iteration Loop | - | - |
| 12 | Production Deploy | - | - |
| 13 | Post-Deploy Audit | execute_quality_gate (gate=QG6) |
QG6 |
| 14 | Scale & Maintain | - | - |
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.
- 2d ago First seen · 112 lines · 0 tokens per session scan A eb7e810137dd
rapp is a command published in the GitHub repository microsoft/aibast-agents-library (7 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,153 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.