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 pnp/copilot-prompts --skill dataverse-fetchxml-buildergit clone --depth 1 https://github.com/pnp/copilot-promptsWrote 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/pnp/copilot-prompts/dataverse-fetchxml-builder)<a href="https://agentmods.dev/skills/pnp/copilot-prompts/dataverse-fetchxml-builder"><img src="https://agentmods.dev/badge/skills/pnp/copilot-prompts/dataverse-fetchxml-builder/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/pnp/copilot-prompts/dataverse-fetchxml-builder"><img src="https://agentmods.dev/badge/skills/pnp/copilot-prompts/dataverse-fetchxml-builder.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 | $0.00054 | $0.02021 |
| Opus 5.5 | $0.00022 | $0.00808 |
| Sonnet 5.5 | $0.00011 | $0.00404 |
| Haiku 4.5 | $0.00005 | $0.00202 |
Grade A, and why
dataverse-fetchxml-builder 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 4d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dataverse FetchXML Builder
Turn a business question into a schema-grounded FetchXML query and explain exactly what each result row represents.
Before Starting
- Question and result shape — requested columns, filters, ordering, and whether one row means a parent record, a related record, or an aggregate group. For troubleshooting, obtain the existing query and expected versus observed behavior.
- Schema evidence — table and column logical names, types, keys, choice values, and join columns from supplied metadata, solution files, or an authorized metadata connection. Display labels alone are insufficient when ambiguous.
- Execution context — raw FetchXML by default; ask when a Power Automate, Web API, SDK, or PAC CLI wrapper is needed. An environment is needed only for live metadata or execution.
Reuse information already supplied or available in the workspace. If the user doesn't provide all details upfront, ask for the missing ones before proceeding. Ask only for information needed for the requested query, and do not ask for credentials in chat.
Output Structure
Produce the query inline or save <query-name>.fetchxml when a file is requested. Accompany it with:
- Intent and schema evidence: result grain, verified names, metadata source, and unresolved assumptions.
- Query explanation: joins, filters, null behavior, ordering, and any aggregate semantics.
- Usage: instructions for the selected execution context only.
- Validation: distinguish XML parsed, schema checked, server executed, and expected-result checked. Include test scope and limitations; execution success alone does not prove correctness.
Step 1: Resolve the schema and meaning
Map each business term to a logical name and data type. Verify relationship direction, primary keys, lookup targets, and choice/state values. Resolve Web API entity-set names from metadata rather than pluralizing logical names.
For live discovery, request only the relevant EntityDefinitions, Attributes, and relationship metadata. Local exports may omit system components; absence from an export does not prove absence from the environment. Treat names found only in examples as illustrative until verified for the user's environment.
What ships with it
4 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.
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.
- 4d ago First seen · 132 lines · 54 tokens per session scan A 5f92b22f752d
dataverse-fetchxml-builder is a skill published in the GitHub repository pnp/copilot-prompts (902 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 2,021 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-03.
dataverse-fetchxml-builder compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dataverse-fetchxml-builderpnp/copilot-prompts | Skill | 902 | 3d ago | MIT | A | 54 | Claude Code, Codex |
| 511-frameworks-micronaut-jdbcjabrena/plinth | Skill | 460 | yesterday | Apache-2.0 | A | 118 | Claude Code, Codex |
| 512-frameworks-micronaut-datajabrena/plinth | Skill | 460 | yesterday | Apache-2.0 | A | 145 | Claude Code, Codex |
| reactive-sync-engine-expertroedyrustam/vibes-plug | Skill | 121 | yesterday | MIT | A | 38 | Cursor |
| search-engine-expertroedyrustam/vibes-plug | Skill | 121 | yesterday | MIT | A | 35 | Cursor |
| system-and-data-designAnastasiyaW/codex-claude-code-config | Skill | 214 | yesterday | MIT | A | 217 | Claude Code |
| azure-openai-patternsfabioc-aloha/Alex_Skill_Mall | Skill | 5 | yesterday | MIT | A | 24 | Claude Code, Codex |