sap-abap-change-assurance

sap-abap-change-assurance is a skill for Claude Code, Codex from Coaspe/sap-abap-mcp. It costs 65 tokens per session (671 once invoked), scanned A, original, MIT.

A read-only quality check for SAP ABAP transport requests, which are bundles of SAP changes moved between systems. It runs ATC checks, ABAP Unit tests, and optional comparisons between systems, then creates machine-readable reports.

In plain words
What is it for?
Use it to review transports, prepare release gates, investigate failed checks, or add SAP change checks to continuous integration.
Why use it?
It provides evidence about whether a transport is ready for release and can expose quality problems before deployment.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the sap-abap-mcp plugin — 2 skills, 1 MCP server shipped together

Good fit Use it to review transports, prepare release gates, investigate failed checks, or add SAP change checks to continuous integration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/coaspe/sap-abap-mcp/sap-abap-change-assurance
Install

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.

Any agent
npx skills add Coaspe/sap-abap-mcp --skill sap-abap-change-assurance
Clone the repo
git clone --depth 1 https://github.com/Coaspe/sap-abap-mcp

Made for: Claude Code, Codex.

Or install sap-abap-mcp, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

Wrote 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.

agentmods badge for sap-abap-change-assurance

README.md
[![agentmods](https://agentmods.dev/badge/skills/coaspe/sap-abap-mcp/sap-abap-change-assurance/github.svg)](https://agentmods.dev/skills/coaspe/sap-abap-mcp/sap-abap-change-assurance)
Your own site
<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.

agentmods 80×15 button for sap-abap-change-assurance

Your own site · 80×15
<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>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 671 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 12d ago against content hash 7f2a66552fcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

plugins/sap-abap-mcp/skills/sap-abap-change-assurance/SKILL.md · 42 lines

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

  1. Call get_connected_systems. Require the user to identify the exact source connectionId if it is not already explicit. Never infer or silently switch systems.

  2. Require a transport number. Ask for a target connectionId only when the user wants a DEV-to-QAS or other landscape comparison.

  3. Call manage_transport_requests with:

    • action: "assess_transport"
    • the exact source connectionId and transportNumber
    • checks: ["atc", "unit_tests"] by default
    • add "target_compare" and targetConnectionId only for an explicit landscape comparison
    • reportFormats: ["json", "sarif", "junit"] when CI evidence is requested
    • maxObjects set high enough for the transport, up to 200
    • failOnAtcWarnings: true only when the user or repository policy makes warnings blocking
  4. If the caller supplied a trusted local CI artifact directory, pass it as reportDirectory. Otherwise use the temporary paths returned by the tool.

  5. Do not call release_transport as 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 than maxObjects. 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.

Read the full file on GitHub · 42 lines

Files

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.

Changes

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.

  1. 12d ago First seen · 42 lines · 65 tokens per session scan A 7f2a66552fcc

Subscribe to this mod's changes

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.