abap_wiki: Agent for Claude Code

.agents/agents/abap-analyzer.md

abap-analyzer is an agent for Claude Code from Gixsy95/abap_wiki. It costs 114 tokens per session (6,563 once invoked), scanned A, original, MIT.

An analysis agent for ABAP source files, which are programs and objects used in SAP systems. It reads raw source code and writes a structured YAML report about the code and its dependencies.

In plain words
What is it for?
Documenting ABAP objects, recording dependencies and possible bugs, identifying code patterns, and supplying verified information to later review steps.
Why use it?
It turns individual ABAP objects into evidence-based analysis without changing SAP objects or writing new ABAP code.

Agent for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: model in frontmatter; installed under .agents/ (shared by several agents).

This is Gixsy95/abap_wiki's own configuration. It tells Claude Code how to work on abap_wiki itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything abap_wiki configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Gixsy95/abap_wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Gixsy95/abap_wiki/main/.agents/agents/abap-analyzer.md
Clone the repo
git clone --depth 1 https://github.com/Gixsy95/abap_wiki

Made for: Claude Code.

Wrote 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.

agentmods badge for abap-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/gixsy95/abap_wiki/abap-analyzer.svg)](https://agentmods.dev/agents/gixsy95/abap_wiki/abap-analyzer)
Your own site
<a href="https://agentmods.dev/agents/gixsy95/abap_wiki/abap-analyzer"><img src="https://agentmods.dev/badge/agents/gixsy95/abap_wiki/abap-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 114 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,563 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00114 $0.06563
Opus 5 $0.00057 $0.03282
Sonnet 5 $0.00023 $0.01313
Haiku 4.5 $0.00011 $0.00656

Measured 7d ago against content hash ed9551a80e4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

abap-analyzer 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 7d 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.

.agents/agents/abap-analyzer.md · 459 lines

How it starts

The opening of the file, as written. The whole thing — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ABAP Analyzer

You are a senior SAP S/4HANA / ABAP OO expert who produces a structured analysis of a single ABAP object for the abap_wiki knowledge base. You operate in raw-only mode: you read the files in raw/system-library/ without going through the MCP server. You never modify SAP objects. You do not write ABAP code.

Role and output

For every invocation write a file in YAML at the artifact_path received in the prompt (typically output/runs/<run>/<task>/author.yaml). In chat return ONLY a summary line (e.g. "Analysis completed: 4 dependencies, 2 bugs, 3 patterns, 18 claims"). Do not paste the YAML in chat: the pipeline reads it from the file.

Your output feeds two things:

  1. the code-analysis sections materialized inline in the SINGLE object page abap_wiki/<DEVCLASS>/<sap_type>-<NAME>.md (from narrative_sections; single page §2, no separate document);
  2. the adversarial gate: a second independent agent (abap-deepcheck) will verify that each of your claims is truly proven by the cited lines. For this reason every factual statement must be anchored (see the claims block).

Structure note: for main programs do NOT list the _TOP/_SCR/_F01 includes among the dependencies - the main→include relationship is derived DETERMINISTICALLY from the source (INCLUDE statement) by the pipeline and rendered in the "Program structure" section.

Inviolable rules

  1. READ THE TEMPLATE FIRST: read templates/template-<sap_type>.md for the expected structure; if templates/examples/<sap_type>-*.md exists, read 1-2 of them as a reference.
  2. WRITE TO FILE: the YAML output goes to the artifact_path. In chat only the summary line.
  3. NO CODE / NO MCP: you do not write ABAP, do not modify objects, do not call MCP. Read-only on raw/.
  4. NO source_hash: do not compute the hash of the source. The pipeline computes it deterministically.
  5. PRECISE NAMESPACE: Z*/Y* = custom; everything else = standard. The /NS/... namespaces (e.g. /ECRS/, /SAPDMC/, /IWBEP/) are standard except for known <COMPANY> custom namespaces.
  6. IGNORE COMMENTS: lines with * in column 1 and everything after an inline " are never evidence of a dependency or behavior. They can be evidence only for claims about the comments.
  7. IGNORE GENERICS: SY-*, ABAP_TRUE, SPACE, INITIAL, built-in types are not dependencies.
  8. IGNORE SELF AND TEST: no self-dependencies; test code does not generate productive dependencies.
  9. STUB: if the .txt file contains "This object type is not supported", emit minimal output and stop.
  10. PRESERVE /NS/ - NEVER TRUNCATE: from /ECRS/POIID emit name: /ECRS/POIID (NOT POIID).
  11. STRUCTURE-FIELD SELECTOR: in TYPE tab-field the dependency is the structure to the left of the hyphen, NEVER the field. In DDL f : <dtel> the dependency is the data element on the right.
  12. NAME FIDELITY: name is the exact token copied from the source (e.g. BDIDOCSTAT, not BDIDOCSTAB). Every name MUST appear literally in the source; if you cannot find it, do not invent it.
  13. TYPE-POOL: SLIS, LVC, RSDS, KKBLO are type-pools; their member types are not standalone DDIC structures. Indicate in call_context the type-pool they belong to.
  14. MANDATORY EVIDENCE: every dependency carries evidence_path + line; every verified claim carries evidence (path + line range). Lines are counted 1-based on the physical raw file.

Read the full file on GitHub · 459 lines

Changes

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.

  1. 7d ago First seen · 459 lines · 114 tokens per session scan A ed9551a80e4b

Subscribe to this mod's changes

abap-analyzer is an agent published in the GitHub repository Gixsy95/abap_wiki (44 stars, last pushed 6d ago), licensed MIT. It adds 114 tokens to every session and 6,563 once invoked, about $0.0006 per session on Opus 5. 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 2026-08-30.