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 shrek-abaper/sap-engineering-skill --skill sap-adt-cligit clone --depth 1 https://github.com/shrek-abaper/sap-engineering-skillWrote 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/shrek-abaper/sap-engineering-skill/sap-adt-cli)<a href="https://agentmods.dev/skills/shrek-abaper/sap-engineering-skill/sap-adt-cli"><img src="https://agentmods.dev/badge/skills/shrek-abaper/sap-engineering-skill/sap-adt-cli/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/shrek-abaper/sap-engineering-skill/sap-adt-cli"><img src="https://agentmods.dev/badge/skills/shrek-abaper/sap-engineering-skill/sap-adt-cli.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 | $0.00116 | $0.02686 |
| Opus 5.5 | $0.00046 | $0.01074 |
| Sonnet 5.5 | $0.00023 | $0.00537 |
| Haiku 4.5 | $0.00012 | $0.00269 |
Grade A, and why
sap-adt-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP ADT CLI
CLI: scripts/sap_adt_cli.py in this skill directory. First run auto-installs
click/requests/urllib3. Always run status first to check the profile and switches.
SKILL_DIR="$(dirname "$(realpath "${BASH_SOURCE[0]:-$0}")")"
SAP_CLI="$SKILL_DIR/scripts/sap_adt_cli.py"
python3 "$SAP_CLI" status
python3 "$SAP_CLI" <command> [args]
# Windows: python "%USERPROFILE%\.agents\skills\sap-adt-cli\scripts\sap_adt_cli.py"
Unconfigured → CONFIG_MISSING (exit 2). First-use credential collection and
non-interactive configure: read references/credentials.md.
Multiple systems/profiles (--profile, SAP_PROFILE, PRD danger of global flags):
read references/profiles.md.
Output contract
Every read command prints a JSON envelope (source commands print plain ABAP by default):
{ "ok": true, "format_version": 1, "command": "get-table", "profile": "dev",
"object": {"type": "table", "name": "VBAK"},
"kind": "fields", "data": { }, "meta": {"row_count": 0} }
Errors on stderr: { "ok": false, …, "error": {"code","message","http_status","hint"} }.
| kind | commands | data shape |
|---|---|---|
source |
get-program/class/function-group/function/include/interface/cds-view/type-group | {source, line_count}; default output = verbatim source |
fields |
get-table, get-structure | {fields:[{name,type,length,decimals,is_key,not_null}]} (S/4 DDL: length null for element refs, listed in meta.unparsed_types; no description key) |
objects |
search-object, get-package, where-used | {objects:[{name,type,uri,package,description}]}; where-used may add optional usage_line/usage_uri |
rows |
run-sql | {columns:[{name,type}], rows:[[…]]} |
records |
list-transports | {transports:[{trkorr,description,status,status_text,owner,target,tasks}]} |
findings |
syntax-check, run-unit-test, run-atc | {findings:[{severity,text,line,uri}]} |
scalar |
get-type-info, get-transaction | object dictionary; type info has resolved_as: domain|dataelement |
capabilities |
discovery | {collections:[{href,title,content_types}]} (Atom discovery; use credentials doctor --coverage for the command matrix) |
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .env.example 5.3 KB
- .gitignore 302 B
- docs/design-session-layer-rejected.md 7.9 KB
- docs/known-issues.md 14 KB
- docs/refactor-handoff.md 11 KB
- docs/refactor-summary.md 17 KB
- README.md 26 KB
- README.zh-CN.md 25 KB
- references/adt_api.md 20 KB
- references/credentials.md 3.7 KB
- references/examples.md 3.9 KB
- references/profiles.md 2.8 KB
- scripts/lib/__init__.py 0 B runs code
- scripts/lib/client.py 4.9 KB runs code
- scripts/lib/config.py 30 KB runs code
- scripts/lib/coverage.py 6.6 KB runs code
- scripts/lib/credentials_reports.py 6.3 KB runs code
- scripts/lib/credentials.py 6.8 KB runs code
- scripts/lib/errors.py 9.4 KB runs code
- scripts/lib/handlers.py 36 KB runs code
- scripts/lib/keystore/__init__.py 2.7 KB runs code
- scripts/lib/keystore/base.py 1.7 KB runs code
- scripts/lib/keystore/dpapi_store.py 5.9 KB runs code
- scripts/lib/keystore/env_store.py 1.6 KB runs code
- scripts/lib/keystore/file_store.py 6.2 KB runs code
- scripts/lib/keystore/keyring_store.py 3.0 KB runs code
- scripts/lib/keystore/pass_store.py 2.9 KB runs code
- scripts/lib/log_redaction.py 3.2 KB runs code
- scripts/lib/output.py 7.2 KB runs code
- scripts/lib/parsers/__init__.py 1.4 KB runs code
- scripts/lib/parsers/capabilities.py 1.1 KB runs code
- scripts/lib/parsers/common.py 1.9 KB runs code
- scripts/lib/parsers/fields.py 4.0 KB runs code
- scripts/lib/parsers/findings.py 9.4 KB runs code
- scripts/lib/parsers/objects.py 4.3 KB runs code
- scripts/lib/parsers/records.py 4.9 KB runs code
- scripts/lib/parsers/rows.py 1.4 KB runs code
- scripts/lib/parsers/scalar.py 2.9 KB runs code
- scripts/lib/parsers/source.py 430 B runs code
- scripts/requirements.txt 272 B
- scripts/sap_adt_cli.py 42 KB runs code
- tests/fixtures/atc.findings.xml 3.1 KB
- tests/fixtures/baseline-exit-codes-current.tsv 1.1 KB
- tests/fixtures/baseline-exit-codes.tsv 383 B
- tests/fixtures/error.403-csrf.txt 28 B
- tests/fixtures/error.403-lock.txt 571 B
- tests/fixtures/error.404-syntaxcheck.txt 113 B
- tests/fixtures/error.404.txt 508 B
- tests/fixtures/error.404.xml 399 B
- tests/fixtures/error.405-usageReferences.raw.xml 389 B
- tests/fixtures/error.405-whereused-legacy.txt 491 B
- tests/fixtures/error.406-list-transports.txt 554 B
- tests/fixtures/error.dml-rejected.txt 154 B
- tests/fixtures/get-class.CL_GUI_FRONTEND_SERVICES.abap 184 KB
- tests/fixtures/get-package.SABP_UNIT.asxml.xml 10 KB
- tests/fixtures/get-package.SABP_UNIT.cli-current.json 3 B
- tests/fixtures/get-structure.VBAKKOM.s4hana.xml 3.0 KB
- tests/fixtures/get-table.REPOSRC.s4hana.xml 1.5 KB
- tests/fixtures/get-table.T001.s4hana.xml 2.3 KB
- tests/fixtures/get-table.VBAK.s4hana.xml 15 KB
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 Changed · -353 lines · -47 tokens per session scan C → A aa24b3300cd0
- 1mo ago Changed · +15 lines c5b9d4195d36
- 1mo ago Changed · +81 lines d5598068fe91
- 1mo ago First seen · 399 lines · 163 tokens per session scan C 2658c7e82f34
sap-adt-cli is a skill published in the GitHub repository shrek-abaper/sap-engineering-skill (44 stars, last pushed 12d ago), licensed MIT. It adds 116 tokens to every session and 2,686 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
abap-cloud
Help with ABAP Cloud development and the clean core level concept (Levels A, B, C, D) including ABAP Cloud vs. classic ABAP development models, ABAP Cloud language version restrictions, wrapper patterns for non-released APIs, released/classic/internal/not-recommended object classification, and clean core principles.…
released-abap-classes
Find released ABAP classes (clean core Level A) for ABAP Cloud Development. Use when user asks about ABAP classes for specific functionality like email, UUID generation, time/date handling, JSON/XML processing, RAP, string processing, random numbers, regex, Base64, HTTP calls, unit testing, PDF rendering, parallel…
abapgit
Help with abapGit workflows including repository setup, cloning, serialization, branching strategies, transport-vs-git workflows, CI/CD integration, and .abapgit.xml configuration. Use when users ask about abapGit, git for ABAP, ABAP version control, abapGit clone, abapGit pull, abapGit push, branching strategy for…
sap-abap-cds
Comprehensive SAP ABAP CDS (Core Data Services) reference for data modeling, view development, and semantic enrichment. Use when creating CDS views or view entities, defining data models with annotations, working with associations and cardinality, implementing input parameters, using built-in functions, writing CASE…
sap-cloud-sdk-ai-python
Integrates the SAP Cloud SDK for AI for Python (sap-ai-sdk-gen, formerly generative-ai-hub-sdk) into Python applications. Use when building Python apps with SAP AI Core, Generative AI Hub, or the Orchestration Service: chat completion, embeddings, streaming, LangChain integration, templating, content filtering, data…
tsv
TSV data processing — view, filter, convert tab-separated data. Zero barrier — use with x-cmd, awk, or Python. Use for "tsv", "tab-separated", "data", "conversion".