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 agentmods add skills/vigneshbarani24/sap-superpowers/development-workflownpx skills add vigneshbarani24/sap-superpowers --skill development-workflowgit clone --depth 1 https://github.com/vigneshbarani24/sap-superpowersWrote 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/vigneshbarani24/sap-superpowers/development-workflow)<a href="https://agentmods.dev/skills/vigneshbarani24/sap-superpowers/development-workflow"><img src="https://agentmods.dev/badge/skills/vigneshbarani24/sap-superpowers/development-workflow.svg" alt="Measured on agentmods" 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 | $0.00037 | $0.02460 |
| Opus 5 | $0.00018 | $0.01230 |
| Sonnet 5 | $0.00007 | $0.00492 |
| Haiku 4.5 | $0.00004 | $0.00246 |
Grade A, and why
development-workflow 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 5d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP Development Workflow
This skill enforces disciplined transport management and landscape governance — it makes landscape-breaking shortcuts impossible, not just inadvisable.
Iron Laws
- NEVER DEVELOP IN PRODUCTION. No exceptions. Not for "urgent fixes." Not for "just a config change." Not for "it's only a text." Production development bypasses QA, creates untraceable changes, and destroys audit trails. One violation invalidates the entire change management process.
- NEVER RELEASE A TRANSPORT WITHOUT TESTING. A transport released to PRD without QAS validation is a production incident waiting to happen. "It worked in DEV" is not testing. QAS confirmation with documented test evidence is testing.
- NEVER MIX OBJECT TYPES IN ONE TRANSPORT. Workbench objects and customizing objects belong in separate transports. Mixed transports create import sequence dependencies that break in production. One transport = one logical unit of change.
- NEVER SKIP THE NAMING CONVENTION. Unnamed or inconsistently named objects become orphaned. When the developer leaves, no one knows what the object does, who owns it, or whether it's safe to delete.
- ALWAYS DOCUMENT THE TRANSPORT BEFORE RELEASE. Description, linked ticket/change request, objects included, and reason for change. A transport with no description is a transport that will cause a production incident investigation to stall.
Rationalization Table
| Agent Will Try To... | Why It Seems Reasonable | Why It Fails | Counter |
|---|---|---|---|
| Suggest a direct PRD fix for "urgent" changes | "It's a 2-minute config change, the normal process takes days" | Emergency PRD changes have caused more production incidents than they've prevented. Every "urgent" shortcut bypasses regression checks. | Iron Law 1. Escalate to the emergency transport process (fast-tracked CTS), not a direct PRD change. |
| Mix workbench and customizing in one transport | "These changes are related, keep them together" | Workbench objects need ABAP import; customizing needs business config import. Mixed transports fail on import sequencing across clients. | Iron Law 3. Separate transports are always required. Link them in the change request, not in the transport. |
| Release to PRD without QAS sign-off | "There's no time, we need this in PRD today" | QAS exists to catch exactly the errors that "seem fine" in DEV. Skipping it means the first test is in production with real users. | Iron Law 2. If the process cannot accommodate QAS testing, the process is broken — escalate to management, don't skip QAS. |
| Create objects in the wrong package | "The default package is fine for now" | Objects in wrong packages lose their transport layer assignment. They become orphaned and cannot be moved to the correct landscape via CTS. | Checklist Step 2: Package assignment is mandatory before any object creation. |
| Skip transport documentation | "Everyone knows what this transport does, it's obvious" | In 6 months, "obvious" becomes "what was this for?" Transport audits, rollbacks, and incident investigations all depend on descriptions. | Iron Law 5. No transport gets released without a description referencing the change request. |
| Use local objects ($TMP) for development | "I'll move them to a proper package later" | Local objects cannot be transported. "Later" becomes never. Development ends up in $TMP and can never reach production. | Checklist Step 2: Assign to a transportable package before development begins. |
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.
- 5d ago First seen · 141 lines · 37 tokens per session scan A 96bc855eb7a1
development-workflow is a skill published in the GitHub repository vigneshbarani24/sap-superpowers (9 stars, last pushed 12d ago), licensed MIT. It adds 37 tokens to every session and 2,460 once invoked, about $0.0002 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
sap-expert
Expert in SAP ERP systems, ABAP programming, SAP HANA, S/4HANA, Fiori applications, and SAP integration patterns including OData, RFC, and IDoc. Use when the user mentions ERP, enterprise, business apps, ABAP, HANA, or S/4HANA, or when the task involves SAP Ecosystem, ABAP Development, Integration Technologies, or…
migrate-from-openclaw
Migrate from OpenClaw to NanoClaw v2. Detects an existing OpenClaw installation, extracts identity, channel credentials, scheduled tasks, and other config, then guides interactive migration. Triggers on "migrate from openclaw", "openclaw migration", "import from openclaw".
add-dial-tool
Give chosen NanoClaw agents a real phone number as a container tool — the dial CLI baked into the agent image plus OneCLI credential injection for api.getdial.ai, scoped per agent, so the agents you pick can send SMS, place AI voice calls, and receive verification codes from inside the sandbox. Independent of the Dial…
add-signal
Add Signal channel integration via signal-cli device-link. Native adapter — no Chat SDK bridge.
slack-agent-flow
Let an existing Slack agent create new agents that arrive as their own Slack bots — provisioned app, operator DM, and a shared three-way room, hot-started without a host restart.
add-deltachat
Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.