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 agentmods add agents/sapdev-ai/sap-dev/abap-developergit clone --depth 1 https://github.com/sapdev-ai/sap-devWhat 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 | $0.00258 | $0.16246 |
| Opus 5 | $0.00129 | $0.08123 |
| Sonnet 5 | $0.00052 | $0.03249 |
| Haiku 4.5 | $0.00026 | $0.01625 |
Grade A, and why
abap-developer 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 2d 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.
The source is not reproduced here
Licensed GPL-3.0
The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 2d ago First seen · 1,053 lines · 258 tokens per session scan A a1fd5949e645
abap-developer is an agent published in the GitHub repository sapdev-ai/sap-dev (7 stars, last pushed 2d ago), licensed GPL-3.0. It adds 258 tokens to every session and 16,246 once invoked, about $0.0013 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 2026-08-31.
Other agents, from other repositories
building-apps
Self-contained, offline reference for AI assistants (and humans) building apps with abap2UI5. It is derived from the framework sources in this repository (src/02/ public API, z2ui5clui5viewbuilder, the hello-world app) and the conventions proven over the 622 ported UI5 demo-kit samples in samples-controls. The…
sap-code-grep
Mechanical, exhaustive grep/count over a mandatory local ABAP source snapshot — MESSAGE statements, branches, AUTHORITY-CHECK, flow-control exits, and log-cell messages. Rejects requests without a complete, readable local source folder. Returns only structured count tables, never raw source dumps.
test-inventory
The specs under node/tests/ load the real app/webapp modules through a stubbed sap.ui.define (loadModule.js, with stubbable module dependencies) — never test a copied function. Run them without a browser.
sap-task-helper
Generic one-shot helper for a bounded, tedious, or high-volume SAP Testing task. The calling agent must provide the exact task, skills to read, artifact paths, allowed writes, and output contract. Suitable for independent sequential or parallel work; never owns phase orchestration or user decisions.
anst-enhancement-analyser
Analyses an xlsx file exported from the ANST Customer Code screen and produces a full customer enhancement inventory — reading source for user exits, definite Z/Y objects, and scanning standard objects for embedded enhancements. Use when the user provides an xlsx path from ANST. The xlsx path MUST be provided by the…
sap-enhancement-research
Finds customer (Z/Y) enhancements — BAdI implementations, enhancement points/sections, classic user-exits — that run inside standard FMs/classes/includes an ABAP program calls, and explains each one in enough detail to write a real test case against it. Use when analyzing an ABAP program/class/transaction for…