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 skills add Ciltress/sap-abap-mcp --skill abap-analyze-modificationgit clone --depth 1 https://github.com/Ciltress/sap-abap-mcpWrote 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/skills/ciltress/sap-abap-mcp/abap-analyze-modification)<a href="https://agentmods.dev/skills/ciltress/sap-abap-mcp/abap-analyze-modification"><img src="https://agentmods.dev/badge/skills/ciltress/sap-abap-mcp/abap-analyze-modification/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ciltress/sap-abap-mcp/abap-analyze-modification"><img src="https://agentmods.dev/badge/skills/ciltress/sap-abap-mcp/abap-analyze-modification.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00197 | $0.04438 |
| Opus 5.5 | $0.00079 | $0.01775 |
| Sonnet 5.5 | $0.00039 | $0.00888 |
| Haiku 4.5 | $0.00020 | $0.00444 |
Grade A, and why
abap-analyze-modification 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 1mo 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 — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analysing SAP standard modifications
Reconstructing what was done to SAP-owned code in a system, from an ADT session. Three independent evidence sources, in this order:
| Source | What only it can tell you | Tool |
|---|---|---|
Table SMODILOG |
The authoritative inventory: every modified object and unit, the operation, user, date, transport | runQuery |
| Modification Assistant markers in the source | The line-level delta, inline, with the transport that made it | readAbapObject / getObjectSource |
| ADT version database | The pre-modification baseline, where one exists | revisions + getObjectSource |
None of them is sufficient alone, and the third is often missing. Say which one an assertion rests on.
Step 1 — the inventory, from SMODILOG
SMODILOG is the Modification Assistant log. It is the only complete list; source markers miss whole
categories of change, and the version DB misses more.
{"tool":"runQuery","args":{"sqlQuery":"SELECT obj_type, obj_name, sub_type, sub_name, operation, mod_user, mod_date, mod_time, trkorr, spau, active FROM smodilog WHERE obj_name LIKE '/IW%' AND operation <> 'NOTE'","rowNumber":500}}
Vary the WHERE to the question: obj_name LIKE 'CL_HTTP%', mod_user = 'DE3190',
trkorr = 'DEVK9A0YSN', mod_date >= '20260101'. runQuery is read-only — the Data Preview service
rejects anything but SELECT.
Verified field layout (describeAbapTable on DEV): 24 fields, key
OBJ_TYPE / OBJ_NAME / SUB_TYPE / SUB_NAME / INT_TYPE / INT_NAME / OPERATION.
OPERATION — the twelve values, from domain CUS_OPER
Read them off the system rather than guessing; these are the fixed values on DEV:
| Value | Meaning | Reading |
|---|---|---|
MOD |
Modifications to sources | Modification Assistant used — a line-level delta exists in the source |
NEW |
New unit | Method/unit added to an SAP object |
ALL |
Unit overlay | Whole unit replaced without assistant delta — the expensive kind |
REPA |
Modification without support | A repair. No delta, no SPAU support |
NOTE |
Note corrections | SAP Note implementation, not a customer modification — filter it out |
IMP |
BAdI implementation | Not a modification |
PRE / POST |
Customer exit at start/end of a unit | Enhancement, not a modification |
ORIG / TORI |
Reset to original | The modification was withdrawn |
TRSL / MIGR |
Translation entry / matchcode migration | Noise for this purpose |
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.
- 1mo ago First seen · 323 lines · 197 tokens per session scan A e435d5278671
abap-analyze-modification is a skill published in the GitHub repository Ciltress/sap-abap-mcp (3 stars, last pushed 6d ago), licensed MIT. It adds 197 tokens to every session and 4,438 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.