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 ClementRingot/LISA --skill lisa-abap-apigit clone --depth 1 https://github.com/ClementRingot/LISAWrote 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/clementringot/lisa/lisa-abap-api)<a href="https://agentmods.dev/skills/clementringot/lisa/lisa-abap-api"><img src="https://agentmods.dev/badge/skills/clementringot/lisa/lisa-abap-api/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/clementringot/lisa/lisa-abap-api"><img src="https://agentmods.dev/badge/skills/clementringot/lisa/lisa-abap-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00150 | $0.01151 |
| Opus 5.5 | $0.00060 | $0.00460 |
| Sonnet 5.5 | $0.00030 | $0.00230 |
| Haiku 4.5 | $0.00015 | $0.00115 |
Grade A, and why
lisa-abap-api scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Never** build a `curl -u user:pass`, read a credential from a `.env`, or put a secret in a How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LISA ABAP API — using zi18n_service
ZCL_I18N_SERVICE (zi18n_service) is one ABAP HTTP service. Every action is a POST of a
JSON body to {base}{path}/{action}, with a single response envelope:
{ "success": true, "data": { … } } // HTTP 200
{ "success": false, "error": { "code": "…", "message": "…" } } // HTTP 400
Default path /sap/bc/http/sap/zi18n_service. Actions: capabilities, list_languages,
list_texts, get_translation, set_translation, compare_translations. Full request/response
shapes, selectors and error codes are in reference.md; the machine-readable
contract is api/zi18n_service.openapi.yaml.
Authentication is out of scope — on purpose
This skill never handles a credential. Something else carries the auth, and the agent only ever sends a JSON body:
- From a BTP runtime (Joule Studio action, CAP, SAP Build): a BTP destination authenticates the call — bind your action to it. Creating that destination (per-user propagation or a shared Basic-auth user, per landscape) is documented in BTP destination setup.
- Want a runtime that holds credentials and exposes the three tools directly? Run the LISA
MCP server (
@lisa-mcp/server) or the ARC-1 extension — the agent calls the tools and never sees a secret.
Never build a curl -u user:pass, read a credential from a .env, or put a secret in a
prompt. If you have no authenticated way to reach the system, stop and point the user at the two
options above — do not improvise auth.
Workflow (pure JSON, whatever the runtime)
- Probe first —
capabilities(body{}) returns the per-action allow-list oftarget_types for THIS system; public cloud and on-premise support different sets. Never assume a type works (an unlisted one fails withCLOUD_UNSUPPORTEDor an XCO error). - Read before writing —
list_textsreturns every slot with apopulatedflag (false= still to translate):{"target_type":"data_element","object_name":"ZMY_DTEL","language":"FR"} - Write with a transport —
set_translationneeds a modifiable transport request the caller's user can record into:{"target_type":"data_element","object_name":"ZMY_DTEL","language":"FR","transport":"A4HK900123","texts":[{"attribute":"short_field_label","value":"Client"}]}
What ships with it
1 file 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.
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 · 73 lines · 150 tokens per session scan A a7cc0bc611b8
lisa-abap-api is a skill published in the GitHub repository ClementRingot/LISA (8 stars, last pushed 3d ago), licensed MIT. It adds 150 tokens to every session and 1,151 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
tongwen
Use when translating engineering CAD drawings between languages — DWG text extraction, glossary-driven translation workspace, QA gating, lossless write-back. Tongwen: local-first CAD/BIM translation suite with an AutoCAD 2019/2021/2025/2026 plugin, a TW-command set, and a headless BatchCli for pipeline use.
backend-internationalization
Use this skill when implementing multi-language support, translation workflows, or locale-aware formatting. This skill enforces: BCP 47 locale tags, ICU MessageFormat for complex messages, dot-separated namespaced keys, fallback chains, and CI-validated translation files. Applies to any backend stack serving…
raqam
Teaches the raqam React number-input library — headless NumberField compound components, useNumberFieldState/useNumberField hooks, Intl presets, locale plugins (fa/ar/bn/hi/th), raqam/server formatting, validation, ScrubArea, accessibility, and form integration. Use when building or debugging currency/percent/unit…
bilingual-doc-sync
Parallel geführte Sprachfassungen eines Dokuments (Paper DE/EN, README + READMEde, SKILL.md + SKILL.en.md, Website-Texte) synchron halten: fehlende Fassung nachziehen, Abschnitts-Parallelität prüfen, Divergenzen beheben — mit klarer Leitsprache-Regel und kontrolliertem Rücktransfer, wenn die Nebenfassung etwas besser…
xcstrings-mcp
Use this skill for ANY task involving iOS/macOS localization: translating strings, adding or removing languages, checking coverage, finding missing or stale translations, validating format specifiers, managing plural forms, migrating from legacy .strings format, exporting/importing XLIFF for external translators…
globalize-now-cli-use
Manage Globalize translation resources using the CLI. Use this skill when the user asks to create a translation project, add or remove languages, connect a GitHub or GitLab repository, manage glossaries or style guides, invite team members, manage API keys, or perform any Globalize platform operation. Also use when…