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 vigneshbarani24/sap-superpowers --skill autopilotgit 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/autopilot)<a href="https://agentmods.dev/skills/vigneshbarani24/sap-superpowers/autopilot"><img src="https://agentmods.dev/badge/skills/vigneshbarani24/sap-superpowers/autopilot/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/vigneshbarani24/sap-superpowers/autopilot"><img src="https://agentmods.dev/badge/skills/vigneshbarani24/sap-superpowers/autopilot.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 | $0.00046 | $0.01959 |
| Opus 5 | $0.00023 | $0.00979 |
| Sonnet 5 | $0.00009 | $0.00392 |
| Haiku 4.5 | $0.00005 | $0.00196 |
Grade A, and why
autopilot 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 9d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP Autopilot — Autonomous Development Pipeline
This skill executes the full ABAP development lifecycle autonomously — from a user's idea to tested, ATC-clean, activated code in a transport. It chains the right skills and agents in sequence, handling errors along the way.
Iron Laws
-
NEVER SKIP THE DESIGN PHASE. Jumping from idea to code produces code that solves the wrong problem. Requirements must be confirmed, data model must be designed, and API dependencies must be identified before any implementation begins.
-
NEVER ACTIVATE WITHOUT TESTS. Code that compiles is not code that works. Every generated class must have unit tests that pass before activation is attempted. Untested activation is shipping hope.
-
NEVER PROCEED PAST A FAILED GATE. If syntax check fails, fix it. If ATC has P1 findings, fix them. If tests fail, fix them. The pipeline does not skip gates — it loops until clean.
-
ALWAYS USE THE SELF-CORRECTING LOOP FOR FIXES. When a gate fails, invoke
self-correcting-loopto iteratively fix → check → fix until clean. Do not manually patch and hope. The loop has discipline you lack. -
ALWAYS PRODUCE A COMPLETION RECORD. When the pipeline finishes, a structured completion record documents every object created, every test result, and the final transport number. No record = pipeline not complete.
Rationalization Table
| Agent Will Try To... | Why It Seems Reasonable | Why It Fails | Counter |
|---|---|---|---|
| Skip requirements confirmation | "The user was very specific" | Users describe what they want, not what they need. Ambiguity hides in specificity. | Confirm requirements explicitly. Repeat back the understanding. Get a yes. |
| Generate code before designing the data model | "I'll figure out the data model as I code" | Retrofitting a data model produces spaghetti dependencies and incorrect CDS view hierarchies. | Complete Step 2 (Design) fully before Step 3 (Generate). |
| Skip unit tests for "simple" methods | "Getters don't need tests" | Getters fail on null refs, auth failures, and data type mismatches. | Iron Law 2. Every method gets a test. No exceptions. |
| Manually fix errors instead of using self-correcting-loop | "I can see the fix, it's obvious" | Manual fixes introduce new errors. The loop catches what you miss. | Iron Law 4. Use the loop. Always. |
| Activate before ATC completes | "ATC is running, but the code looks clean" | ATC catches what syntax check misses — performance issues, security holes, deprecated APIs. | Wait for ATC. No activation without P1/P2 clean. |
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.
- 9d ago First seen · 194 lines · 46 tokens per session scan A 53b7ba0fe5c0
autopilot is a skill published in the GitHub repository vigneshbarani24/sap-superpowers (9 stars, last pushed 17d ago), licensed MIT. It adds 46 tokens to every session and 1,959 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.