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 abapgit 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)<a href="https://agentmods.dev/skills/ciltress/sap-abap-mcp/abap"><img src="https://agentmods.dev/badge/skills/ciltress/sap-abap-mcp/abap/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"><img src="https://agentmods.dev/badge/skills/ciltress/sap-abap-mcp/abap.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 | $0.00184 | $0.01598 |
| Opus 5 | $0.00092 | $0.00799 |
| Sonnet 5 | $0.00037 | $0.00320 |
| Haiku 4.5 | $0.00018 | $0.00160 |
Grade A, and why
abap 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 10d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ABAP
Check and improve ABAP code quality using three complementary approaches:
- The system's own checks — ABAP syntax check and ATC, via the ABAP ADT MCP server. Authoritative: they know the DDIC, the release and what will actually activate.
- abaplint: static analysis via CLI over serialized (abapGit) files. The right tool in CI, or when there is no system to talk to.
- Clean ABAP: manual review against the style guide, for everything no tool can decide.
Step 0 — is there a system?
Check whether the ABAP ADT MCP server's tools are available (readAbapObject, syntaxCheckCode,
createAtcRun).
- Yes → prefer the system's checks. Read
references/mcp-adt-tools.mdand follow it: fetch the source by name withreadAbapObject, runsyntaxCheckCode, run ATC, then do the Clean ABAP review for the judgement calls. Do not ask the user to paste code you can read yourself. - No → use the abaplint workflow below plus the Clean ABAP review.
Either way the Clean ABAP review still applies — only the mechanical checks differ.
Workflow
-
Determine check type based on user request:
- If the user asks to run ATC or check against the system: use ATC (
references/mcp-adt-tools.md) - If the user asks to lint, run abaplint, or check syntax: use the syntax check with a system, abaplint without one
- If the user asks for clean code review, best practices, or code quality: use Clean ABAP review
- If unclear or the user asks for a full check: use all that are available
- If the user asks to run ATC or check against the system: use ATC (
-
For abaplint checks:
- Verify
abaplintis installed (npx @abaplint/cli --versionorabaplint --version) - If not installed, install with:
npm install @abaplint/cli -g - Check if
abaplint.jsonexists in the project root - If no config exists, help the user create one (see starter configs in
references/abaplint.md) - Run
abaplintin the project root directory - Parse and present findings to the user
- Verify
What ships with it
5 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.
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.
- 10d ago First seen · 179 lines · 184 tokens per session scan A b6b9c9099317
abap is a skill published in the GitHub repository Ciltress/sap-abap-mcp (3 stars, last pushed 17d ago), licensed MIT. It adds 184 tokens to every session and 1,598 once invoked, about $0.0009 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 skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.