Analyze Cbo Obj

SC4SAP Analyze CBO Objects

Walks a CBO (Customer Business Object) package, inventories every project-built ABAP element (table, structure, data element, class, interface, function module, program, view, table type), detects which elements are frequently reused inside the package, infers each element's business purpose from its name/fields/descriptions, and persists the result to .sc4sap/cbo/<MODULE>/<PACKAGE>/ for downstream skills (program, program-to-spec, create-object, autopilot) to consult before creating anything new.

<Response_Prefix> Every response triggered by this skill MUST begin with [Model: <main-model> · Dispatched: <sub-summary>] per ../../common/model-routing-rule.md § Response Prefix Convention. </Response_Prefix> <Target_Object>The target object is looked up on the active profile's system only. Not found → stop and ask per ../../common/multi-profile-artifact-resolution.md § Target object not on the active system — never substitute a similar name, never switch profiles on your own.</Target_Object>

<Phase_Banner> Multi-phase skill. Before each Agent(...) dispatch, emit ▶ phase=<id> (<label>) · agent=<name> · model=<Opus|Sonnet|Haiku> per ../../common/model-routing-rule.md § Phase Banner Convention. Resolve the dispatch mode first per ../../common/model-dispatch-mode.md: auto (default) uses the model below/in the rule; user-defined asks the user Opus / Sonnet / Haiku (recommended one first) before each dispatch group. </Phase_Banner>

<Use_When>

• Starting development on a module that already has a sizeable Z-package
• Onboarding onto an AMS / support engagement (need a map of custom assets)
• Before /sc4sap:create-program or /sc4sap:create-object on a new spec — so reuse is evaluated
• User says "analyze CBO", "analyze custom objects", "map Z package", "list frequently used customs", "CBO inventory" </Use_When>

<Do_Not_Use_When>

• User wants a code quality review of one object → /sc4sap:analyze-code
• User wants to reverse-engineer ONE program into a spec → /sc4sap:program-to-spec
• User wants to create an object → /sc4sap:create-object
• Package does not yet contain custom objects (CBO discovery is not meaningful) </Do_Not_Use_When>

<Session_Trust_Bootstrap> MANDATORY — runs as Step 0 before any MCP call or user interaction.

Invoke /sc4sap:trust-session with parent_skill=sc4sap:analyze-cbo-obj to pre-grant all MCP tool + file-op permissions for this session (eliminates per-tool "Allow this tool?" prompts during the 8-step walk).

• If .sc4sap/session-trust.log already has a line within the last 24h, skip silently.
• Otherwise run it and surface the one-line confirmation.

Full spec: see ../trust-session/SKILL.md. </Session_Trust_Bootstrap>

<Workflow_Steps> Orchestration is 3 main-thread Socratic steps + a delegated stocking pass (sap-stocker walk → sap-checker scout fan-out → reference graph + usage → sap-stocker finalize) + a branching hand-off. Detailed spec lives in workflow-steps.md.

• Step 1 / 1.5 / 2 (main thread) — Socratic intake: package name → flagship programs (optional <KEY_PROGRAMS>) → module. The main thread follows the session model (model: inherit).
• Step 3–7 (delegated · Sonnet + Haiku) — sap-stocker MODE: walk writes walk.json; for packages with ≥ 30 objects, Haiku sap-checker × N collect in-package callers + DDIC signals per batch in parallel (scout-facts.md); Step G fetches sources and builds graph.json from source, TCodes and DDIC, plus on ECC usage-result.json from ST03N TCode usage and batch jobs (graph-usage.md); sap-stocker MODE: finalize does the rest. Spec: stocker-fanout.md. Together they run the stocker's Investigation_Protocol: walk → reference graph (GetWhereUsed on S/4, graph.json on ECC) → pin/frequency tiering → business-purpose inference → cross-module gap analysis (per ../../common/active-modules.md) → sensitive-name flagging → persist index.md + inventory.json → return a Logic-heavy: <bool> flag. Authoritative spec: ../../agents/sap-stocker.md § Investigation_Protocol + § Output_Format.
• Step 8 (branching):
  • Branch A (Logic-heavy: false, DDIC-dominant) — canned summary printed by main thread. No agent dispatch.
  • Branch B (Logic-heavy: true, FM/CLAS/INTF/large-PROG in inventory) — main thread renders a reader-facing briefing from inventory.json: pinned highlights · business-logic assets · cross-module gaps · sensitive objects · next-step hint. No extra agent dispatch.

Main thread NEVER calls GetPackageContents / GetWhereUsed itself for the inventory pass — that context stays inside the stocker and checker agents so the orchestrator window remains small even for large packages (200+ objects). </Workflow_Steps>

<Output_Files>

Copy code
.sc4sap/cbo/
└── <MODULE>/               # SD, MM, PP, PM, QM, WM, TM, TR, FI, CO, HCM, BW, PS, Ariba
    └── <PACKAGE>/          # e.g., ZSD_MAIN
        ├── index.md        # human-readable summary, grouped by object type
        ├── index.html      # optional single-file HTML view of index.md (offered at Step 8)
        ├── inventory.json  # machine-readable, consumed by sibling skills
        ├── walk.json       # package member list + scout batches (stocker walk)
        ├── scout-facts.md  # Haiku checker FACT lines (only for packages with ≥ 30 objects)
        └── raw-walk.md     # optional full walk (only if asked or small package)

</Output_Files>

<MCP_Tools_Used>

• Discovery: GetPackage, GetPackageContents, GetPackageTree, SearchObject, GetObjectsByType
• Object detail: GetTable, GetStructure, GetDataElement, GetDomain, GetView, GetClass, GetInterface, GetFunctionGroup, GetFunctionModule, GetProgram, GetObjectInfo
• Usage graph: GetWhereUsed
• NEVER used by this skill: GetTableContents, GetSqlQuery (no row data — DDIC metadata only) </MCP_Tools_Used>

<Related_Skills>

• /sc4sap:create-program — reads .sc4sap/cbo/<MODULE>/<PACKAGE>/inventory.json during spec drafting to prefer existing CBO elements
• /sc4sap:program-to-spec — same, for reverse-engineering
• /sc4sap:create-object — same, to suggest reuse before creation
• /sc4sap:analyze-code — quality review of ONE object (complementary, not overlapping) </Related_Skills>

<Data_Extraction_Safety> This skill only reads DDIC metadata and where-used relations. It MUST NOT call GetTableContents or GetSqlQuery. Row-level access stays behind the standard blocklist + acknowledge_risk gate. See common/data-extraction-policy.md. </Data_Extraction_Safety>

Task: $ARGUMENTS