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/rapp-stepgit clone --depth 1 https://github.com/microsoft/aibast-agents-libraryWrote 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.
[](https://agentmods.dev/commands/microsoft/aibast-agents-library/rapp-step)<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01086 |
| Opus 5 | $0.00000 | $0.00543 |
| Sonnet 5 | $0.00000 | $0.00217 |
| Haiku 4.5 | $0.00000 | $0.00109 |
Grade A, and why
rapp-step scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RAPP Step Guide
Guide the user through a specific RAPP pipeline step. The argument should be the step number (1-14).
All operations use the single RAPP agent with different actions.
Step Details
Based on the step number provided ($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 guideprocess_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 proposalgenerate_full_mvp_document- Complete customer-ready documentprioritize_features- Feature prioritizationdefine_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 codegenerate_agent_metadata- Metadata schema only Inputs needed: agent_name, agent_description, features, data_sources Outputs: Complete Python agent code
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.
- 3d ago First seen · 108 lines · 0 tokens per session scan A 7ef94f0bcffb
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.
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.