# Sc4sap:team

> N coordinated SAP agents on a shared task list using Claude Code native teams

- **Type:** Skill
- **Install:** `agentstack add skill-babamba2-superclaude-for-sap-team`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [babamba2](https://agentstack.voostack.com/s/babamba2)
- **Installs:** 0
- **Category:** [Communication](https://agentstack.voostack.com/c/communication)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [babamba2](https://github.com/babamba2)
- **Source:** https://github.com/babamba2/superclaude-for-sap/tree/main/skills/team

## Install

```sh
agentstack add skill-babamba2-superclaude-for-sap-team
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# SC4SAP Team

Follows OMC `team` pattern adapted for SAP. Coordinates multiple specialized SAP agents working in parallel on a shared task list using Claude Code native team mode.

sc4sap:team spins up N coordinated agents that divide and conquer a SAP development task. Each agent is assigned a role (sap-developer, sap-code-reviewer, sap-transport-manager, etc.) and works on its slice of the task list simultaneously, with results merged at the end.

Every response triggered by this skill MUST begin with `[Model:  · Dispatched: ]` per [`../../common/model-routing-rule.md`](../../common/model-routing-rule.md) § Response Prefix Convention.

Multi-phase skill. Before each `Agent(...)` dispatch (including every parallel spawn), emit `▶ phase= () · agent= · model=` per [`../../common/model-routing-rule.md`](../../common/model-routing-rule.md) § Phase Banner Convention.

- Task has multiple independent SAP objects to create or modify (e.g., class + interface + unit test)
- User wants parallel development across multiple ABAP programs or packages
- Large transport release requiring parallel validation across multiple objects
- User says "team", "parallel", "all at once", or "split the work"

- Task is sequential (one object depends on another) -- use `/sc4sap:create-program` (for a full program with ordered includes) or `/sc4sap:create-object` repeatedly
- Single object creation or modification -- delegate directly to executor
- User wants to review options first -- use `/sc4sap:deep-interview` to crystallize the spec before dispatching agents

Available roles to assign to team members:
- `sap-developer`: Writes and activates ABAP code via MCP (CreateClass, UpdateClass, RunUnitTest, etc.)
- `sap-code-reviewer`: Reviews ABAP code quality, naming conventions, and SAP best practices
- `sap-transport-manager`: Handles CTS transport creation, assignment, and release via ListTransports, GetTransport, CreateTransport
- `sap-architect`: Designs ABAP object structure, package hierarchy, and dependency graph
- `sap-tester`: Writes and runs ABAP unit tests via CreateUnitTest, RunUnitTest, GetUnitTestResult

- Assign agents to non-overlapping task slices to avoid transport conflicts
- Each agent must confirm transport assignment before writing objects
- Merge results: collect activation status from each agent before team completion
- If any agent reports activation failure, halt and escalate to orchestrator
- Use `run_in_background: true` for long-running unit test suites

1. Parse task into independent work slices (by ABAP object or package)
2. Assign one agent per slice with explicit role and task scope
3. Each agent: create/modify objects -> activate -> run unit tests -> report status
4. Orchestrator: collect all agent results, verify zero inactive objects remain
5. If all pass: report completion summary with object list and transport number
6. If any fail: surface errors and retry failed slices

Task: {{ARGUMENTS}}

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [babamba2](https://github.com/babamba2)
- **Source:** [babamba2/superclaude-for-sap](https://github.com/babamba2/superclaude-for-sap)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-babamba2-superclaude-for-sap-team
- Seller: https://agentstack.voostack.com/s/babamba2
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.