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 orchestra-hq/orchestra-skills --skill powerbi-prefect-to-orchestragit clone --depth 1 https://github.com/orchestra-hq/orchestra-skillsWrote 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/orchestra-hq/orchestra-skills/powerbi-prefect-to-orchestra)<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/powerbi-prefect-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/powerbi-prefect-to-orchestra/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/orchestra-hq/orchestra-skills/powerbi-prefect-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/powerbi-prefect-to-orchestra.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 | $0.00146 | $0.02334 |
| Opus 5.5 | $0.00058 | $0.00934 |
| Sonnet 5.5 | $0.00029 | $0.00467 |
| Haiku 4.5 | $0.00015 | $0.00233 |
Grade A, and why
powerbi-prefect-to-orchestra scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
resp = requests.post( How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
There is no official Prefect Power BI block or collection. Power BI refresh tasks in Prefect are always hand-rolled @task functions that (1) acquire an Azure AD token for a service principal — usually via msal.ConfidentialClientApplication — and (2) call the Power BI REST API directly with requests (or httpx) to trigger a dataset or dataflow refresh and poll its status. This skill converts that pattern into Orchestra pipeline tasks using the POWER_BI integration. Authentication (tenant ID, client ID/application ID, client secret) moves from environment variables inside the task to a named Orchestra Power BI connection.
Parameter Mapping
| Prefect construct | Orchestra field | Notes |
|---|---|---|
msal.ConfidentialClientApplication(client_id, client_credential, authority=f".../{tenant_id}") |
connection: |
Orchestra Power BI connection holds tenant ID, client ID, and client secret (Azure service principal) |
POST /v1.0/myorg/groups/{group_id}/datasets/{dataset_id}/refreshes |
integration_job: POWER_BI_REFRESH_DATASET + parameters.dataset_id |
group_id in the URL path maps to parameters.workspace_id — leave null unless it varies from the connection's workspace, see Gotchas |
POST /v1.0/myorg/groups/{group_id}/dataflows/{dataflow_id}/refreshes |
integration_job: POWER_BI_REFRESH_DATAFLOW + parameters.dataflow_id |
Same group_id → workspace_id mapping — leave null unless it varies from the connection's workspace |
JSON body {"notifyOption": "MailOnFailure"} or similar |
(dropped) | Not a valid Orchestra parameter — Orchestra pipeline alerts: replaces failure notification, see below |
JSON body {"type": "Full"} or refreshRequest.type |
parameters.refresh_type |
Optional — one of Full, ClearValues, Calculate, DataOnly, Automatic, Defragment |
polling loop (GET .../refreshes/{id} until Completed/Failed) |
(always) | Orchestra's task already waits for completion |
retries / retry_delay_seconds on @task |
configuration.retries / configuration.retry_delay |
Under configuration: block — retry_delay is integer MINUTES (not seconds); convert by dividing by 60, cap at 120 |
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.
- 2mo ago First seen · 160 lines · 146 tokens per session scan A 414b0f36a87d
powerbi-prefect-to-orchestra is a skill published in the GitHub repository orchestra-hq/orchestra-skills (9 stars, last pushed yesterday), licensed MIT. It adds 146 tokens to every session and 2,334 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
powerbi-prefect-to-orchestra compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| powerbi-prefect-to-orchestraorchestra-hq/orchestra-skills | Skill | 9 | yesterday | MIT | A | 146 | Claude Code |
| agent-platform-model-registrygoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| foundry-config-setupmicrosoft/agent-framework | Skill | 15k | yesterday | MIT | A | 65 | Claude Code, Codex |
| google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 132 | Claude Code, Codex |
| training-checkwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 35 | Claude Code |
| nemo-automodel-launcher-configNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code |
| finetuningmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 132 | Claude Code |