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 MarioDeFelipe/sap-datasphere-plugin-for-claude-cowork --skill datasphere-flow-doctorgit clone --depth 1 https://github.com/MarioDeFelipe/sap-datasphere-plugin-for-claude-coworkWrote 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/mariodefelipe/sap-datasphere-plugin-for-claude-cowork/datasphere-flow-doctor)<a href="https://agentmods.dev/skills/mariodefelipe/sap-datasphere-plugin-for-claude-cowork/datasphere-flow-doctor"><img src="https://agentmods.dev/badge/skills/mariodefelipe/sap-datasphere-plugin-for-claude-cowork/datasphere-flow-doctor/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/mariodefelipe/sap-datasphere-plugin-for-claude-cowork/datasphere-flow-doctor"><img src="https://agentmods.dev/badge/skills/mariodefelipe/sap-datasphere-plugin-for-claude-cowork/datasphere-flow-doctor.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 | $0.00052 | $0.08637 |
| Opus 5 | $0.00026 | $0.04319 |
| Sonnet 5 | $0.00010 | $0.01727 |
| Haiku 4.5 | $0.00005 | $0.00864 |
Grade A, and why
Flow Doctor 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 — 1,300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flow Doctor
Overview
The Flow Doctor skill guides you through systematic troubleshooting of SAP Datasphere flows. When a flow fails, this skill helps you read error messages, understand root causes, and implement targeted solutions.
When to Use This Skill
- Flow execution failed: Red status in monitor, need to identify why
- Partial data loading: Only some records loaded, others rejected
- Performance degradation: Flow taking longer than expected
- Connectivity issues: Cannot reach source or target system
- Memory errors: Out-of-memory or resource constraints
- Data mismatches: Unexpected differences between source and target
- Schema changes: Source structure changed, flow now incompatible
- Task chain failures: Dependent tasks failing or not executing
Systematic Troubleshooting Workflow
Step 1: Check Overall Flow Status
Datasphere → Data Integrations → Monitor
└─ Find failing flow
├─ Note last run time and status
├─ Check error indicator (red icon)
└─ Count failed runs vs total runs
Status Indicators:
| Status | Meaning | Action |
|---|---|---|
| GREEN | Running successfully | Check logs for warnings |
| YELLOW | Running but with warnings | Review warning messages |
| RED | Failed | Read error log immediately |
| GRAY | Not running | Check scheduling or manual trigger |
| BLUE | Running (in progress) | Wait for completion |
Example Status Review:
Flow: REP_CUSTOMER_DAILY
Status: RED (Failed)
Last Run: 2024-01-16 23:45:00
Duration: 12 minutes (usually 5 minutes - 2.4x longer!)
Records: 45,000 / 1,000,000 loaded
Error Count: 1
Step 2: Access and Read Error Logs
Location: Data Integrations → Monitor → [Flow Name]
Error Log Details:
├─ Timestamp: 2024-01-16 23:45:45
├─ Severity: ERROR
├─ Message: "Memory limit exceeded"
├─ Step: "LOAD_DATA_TRANSFORM"
└─ Context: "Processing batch 3 of 10"
Log Types by Flow Type:
Replication Flow Logs:
[2024-01-16 23:45:12] INFO | Initializing replication from S/4HANA
[2024-01-16 23:45:30] INFO | Connected to source system
[2024-01-16 23:45:31] INFO | Extracting C_CUSTOMER (1M rows)
[2024-01-16 23:46:00] WARN | Extraction slow: 20K rows/min (target: 50K rows/min)
[2024-01-16 23:46:45] ERROR | Authorization error: User missing RFC_READ_TABLE
[2024-01-16 23:46:45] INFO | Replication failed - 0 rows loaded
What ships with it
7 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.
- references/abap-side-monitoring.md 26 KB
- references/conversion-error-workaround.md 4.0 KB
- references/error-catalog.md 23 KB
- references/load-type-scenarios.md 5.6 KB
- references/odp-replication-troubleshooting.md 6.7 KB
- references/replication-flow-error-patterns.md 13 KB
- references/slt-replication-troubleshooting.md 10 KB
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 · 1,300 lines · 52 tokens per session scan A 2b0d808cb8ef
Flow Doctor is a skill published in the GitHub repository MarioDeFelipe/sap-datasphere-plugin-for-claude-cowork (26 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 8,637 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 2026-08-30.
Other skills, from other repositories
spark-optimization
Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.
notebooklm
Install, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed async Python API. Use for notebook and source management, grounded chat and research, and artifact generation or download when the user mentions Gemini Notebook, notebooklm-py, the notebooklm CLI, or its Python API.…
debug-inference
Debug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM. Use for provider attachment, endpoint policy, credential substitution, topology, and migration from the removed inference.local endpoint. Trigger…
oh-my-posh
Install, configure, or troubleshoot Oh My Posh/ohmyposh: shell init, themes, segments, Nerd Font icons, and prompt setup on PowerShell, zsh, bash, or fish.
eagle3-triage
Triage a failed EAGLE3 pipeline run. Identifies which step failed (data synthesis, hidden state dump, training, or benchmark), diagnoses root cause from logs, and suggests fixes. Use when user reports an EAGLE3 pipeline failure or asks why a specific step failed. Also helps debug new model support issues.
trulens-instrumentation
Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization.