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 Coaspe/sap-abap-mcp --skill sap-abap-change-assurancegit clone --depth 1 https://github.com/Coaspe/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/coaspe/sap-abap-mcp/sap-abap-change-assurance)<a href="https://agentmods.dev/skills/coaspe/sap-abap-mcp/sap-abap-change-assurance"><img src="https://agentmods.dev/badge/skills/coaspe/sap-abap-mcp/sap-abap-change-assurance/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/coaspe/sap-abap-mcp/sap-abap-change-assurance"><img src="https://agentmods.dev/badge/skills/coaspe/sap-abap-mcp/sap-abap-change-assurance.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 | $0.00065 | $0.00671 |
| Opus 5 | $0.00032 | $0.00336 |
| Sonnet 5 | $0.00013 | $0.00134 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
sap-abap-change-assurance 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 12d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP ABAP change assurance
Assess a transport through live, read-only ADT checks. Keep the assessment distinct from the destructive release action.
Run the assessment
-
Call
get_connected_systems. Require the user to identify the exact sourceconnectionIdif it is not already explicit. Never infer or silently switch systems. -
Require a transport number. Ask for a target
connectionIdonly when the user wants a DEV-to-QAS or other landscape comparison. -
Call
manage_transport_requestswith:action: "assess_transport"- the exact source
connectionIdandtransportNumber checks: ["atc", "unit_tests"]by default- add
"target_compare"andtargetConnectionIdonly for an explicit landscape comparison reportFormats: ["json", "sarif", "junit"]when CI evidence is requestedmaxObjectsset high enough for the transport, up to 200failOnAtcWarnings: trueonly when the user or repository policy makes warnings blocking
-
If the caller supplied a trusted local CI artifact directory, pass it as
reportDirectory. Otherwise use the temporary paths returned by the tool. -
Do not call
release_transportas part of this skill. Release is a separate mutation requiring an explicit user request and exact transport-number confirmation.
Interpret the gate
passed: Every requested applicable check completed, no blocking ATC finding or ABAP Unit failure occurred, and the transport was not truncated. ATC warnings may still appear when they are non-blocking.failed: A blocking ATC result or ABAP Unit failure occurred. Summarize the affected objects and findings; do not recommend release.incomplete: A requested check failed to execute, a class had no discoverable tests, the transport contained no objects, ATC findings were truncated, or more objects existed thanmaxObjects. Never present an incomplete result as a pass.
Treat targetComparison.status: "different" as evidence of the expected source delta, not automatically as a defect. Treat missing as a risk that needs human review. Report error as incomplete evidence.
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.
- 12d ago First seen · 42 lines · 65 tokens per session scan A 7f2a66552fcc
sap-abap-change-assurance is a skill published in the GitHub repository Coaspe/sap-abap-mcp (4 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 671 once invoked, about $0.0003 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
transport-release-gate
Run a quality gate over an SAP transport request before it is released — collect the TR's objects, check for inactive objects and foreign locks, run syntax checks, ATC, and unit tests, then produce a structured go/no-go report. Use whenever the user wants to release a transport, asks "is this TR safe to release?"…
unit-test-bootstrapper
Analyzes source code files (Python, JS, TS) and auto-generates comprehensive, robust unit tests covering happy paths, edge cases, and exceptions.
add-test
Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.
cpp-testing
Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.