Agent guidance
Narrows to classic systems, where the question is often what an agent may touch at all rather than which pattern it should follow. claude-sap-kitclaude-sap-kitA Claude Code plugin of three skills that extends arc-1 with five Custom_* tools for an on-premise ABAP system: running a report and reading its ALV as JSON, previewing a NAST message as PDF, and reading, writing and replacing SmartForms as XML.independent, abap reaches the surfaces its README says ADT does not cover, running a report, previewing print output and editing SmartForms; sap-basis-opssap-basis-opsBasis and technical operations at the OS and database layer — the sysadmin plane every other SAP skill set skips — as runbook skills that emit a source-cited command sequence with its pre- and post-checks.independent, abap writes runbooks for the operating system and database beneath the stack and leaves running them to somebody else; and SuperClaude for SAPSuperClaude for SAPA Claude Code plugin that installs and wires its own ABAP MCP server, then puts a two-layer write guard between the agent and any system profile marked QA or production.independent, abap labels each registered system so a write against QA or production is blocked in two places rather than one.
Showing artifacts, examples and content with confirmed Standard ABAP applicability. View All ABAP
Overview
No core answer is documented.
Not covered: At the independent sets that state this flavor in their own words. claude-abap-devclaude-abap-devFive ABAP workflows for Claude Code — ATC fixing, a clean-core audit, a Clean ABAP review, ABAP Unit and debugging — that ship no system access of their own and run on whichever community MCP servers are already configured.independent, abap records the system it was tried against, S/4HANA 2023 on premise, and carries five workflows for ATC remediation, a clean core audit, a Clean ABAP review, ABAP Unit and debugging; claude-sap-kitclaude-sap-kitA Claude Code plugin of three skills that extends arc-1 with five Custom_* tools for an on-premise ABAP system: running a report and reading its ALV as JSON, previewing a NAST message as PDF, and reading, writing and replacing SmartForms as XML.independent, abap reaches the three things its README says ADT does not cover, running a report, previewing NAST print output and editing SmartForms; sap-basis-opssap-basis-opsBasis and technical operations at the OS and database layer — the sysadmin plane every other SAP skill set skips — as runbook skills that emit a source-cited command sequence with its pre- and post-checks.independent, abap covers the operating system and database beneath the stack; and SuperClaude for SAPSuperClaude for SAPA Claude Code plugin that installs and wires its own ABAP MCP server, then puts a two-layer write guard between the agent and any system profile marked QA or production.independent, abap registers a landscape of systems and blocks writes against the ones labelled QA or production.
Community-only is a reading of this door's own providers and not a quote from the core. rap-skillsrap-skillsRAP skills delivered branch-per-target, so the playbook you check out only references patterns valid for your deployment — managed on BTP, unmanaged with BAPI wrappers, and S/4HANA Cloud editions planned.independent, abap declares a branch for S/4HANA on-premise as planned, which would state this flavor when it lands.
Artifacts
Tasks
Get an agent to write ABAP that follows Clean ABAP
A developer wants the ABAP an agent writes to follow SAP's Clean ABAP conventions without the rules being pasted into the prompt each time, and wants what it wrote read back against them.
About how the conventions reach the agent and in what shape. The conventions themselves are Clean ABAP and belong to clean code; running a linter or ATC over the result mechanically is static analysis. Whether the code a reader gets is actually clean is not something any of these records establishes.
claude-abap-devA sequence of tool calls rather than a rule file: abaplint for the mechanical rules beside a reasoned read for what a linter misses, with each rule cited to the Clean ABAP style guide. The skills find their servers by tool name, so the review runs against whichever ABAP MCP server a person already has configured rather than one this ships.
Conditions: At least one of mcp-abap-adt or vibing-steampunk is connected, which is where the source comes from An abaplint MCP server exposing LintAbap and FixAbap, or the public abaplint command line, for the lint step
Remaining work: Connect the servers. Without system access the workflow has no source to read, and without abaplint the mechanical half of the review does not run.
Work on ABAP with an agent and no system connection
A developer wants to review, write or test ABAP with an agent on a machine that has no connection to an SAP system — a serialised repository checked out, or source pasted into the session, and nothing else.
About what an agent has to work with when nothing is connected: the packaged knowledge it is handed, and the tooling that does on the local machine what a system would otherwise do. What a connected agent can read, change, activate or run in a live system is agent access to your code, and an entry that offers both is assessed here for its off-system half only. This record does not say that working without a system is equivalent to working with one, and the contributions state where the difference falls.
sap-basis-opsThe guidance is complete without any reach of its own: each skill produces the command sequence for a given system, database and operating system, cited to its source and with the checks to run before and after, and running it is a separate decision that goes through an SSH or shell server the person supplies. The skills bundle no credentials and the repository states they never auto-run a destructive command.
Remaining work: Read the sequence and run it yourself, or connect the shell server and approve each step. The commands it writes stop systems and delete data, which is why execution is deliberately somebody else's decision.
Content
Details
Coverage
Designs that place it
Comparison properties
These are the questions used to compare what the artifacts do. Values come from their documentation and may apply to a particular ecosystem or runtime. Each recorded value in the comparison opens its statement and sources.
For your agent
- Ref
capability:agent-guidance- JSON
- /capabilities/agent-guidance.json
- MCP
- Connecting an agent