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 Kilo-Org/kilo-marketplace --skill powerbi-mcpgit clone --depth 1 https://github.com/Kilo-Org/kilo-marketplaceWrote 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/kilo-org/kilo-marketplace/powerbi-mcp)<a href="https://agentmods.dev/skills/kilo-org/kilo-marketplace/powerbi-mcp"><img src="https://agentmods.dev/badge/skills/kilo-org/kilo-marketplace/powerbi-mcp/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/kilo-org/kilo-marketplace/powerbi-mcp"><img src="https://agentmods.dev/badge/skills/kilo-org/kilo-marketplace/powerbi-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 31 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 163 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- low Excessive Agency · line 163 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00055 | $0.01473 |
| Opus 5 | $0.00028 | $0.00737 |
| Sonnet 5 | $0.00011 | $0.00295 |
| Haiku 4.5 | $0.00006 | $0.00147 |
Grade A, and why
powerbi-mcp 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Power BI MCP Safety and Execution Protocol
The agent proposes, the user approves, and then the agent executes. Apply this protocol to every Power BI MCP session.
Architecture Boundary
- Report layer: visuals, charts, colors, tooltips, and formatting. Provide manual specifications only.
- Power Query / M layer: data sources and transformations. Draft M code for manual application; do not apply it through semantic-model tools.
- Semantic model layer: DAX measures, tables, relationships, roles, and TMDL. This is the MCP read/write scope.
Action Tiers
Tier 1: Read-only
No confirmation is required, but announce the read scope. Examples: schema and metadata reads, dependency analysis, row counts, data-quality queries, TMDL export, and drafting unapplied DAX or M.
Tier 2: Structural write
Confirm before creating or modifying measures, calculated objects, relationships, folders, format strings, or RLS roles and rules.
Use this template:
Proposed Power BI change (Tier 2)
Target: <workspace/model and object names>
Changes: <itemized changes>
Validation: <checks to run afterward>
Rollback: <backup/TMDL restore approach>
Reply YES to apply exactly these changes. Any scope change requires a new proposal.
Tier 3: Destructive or broad write
Require a confirmed save/export checkpoint, itemize every object, and confirm before execution. Tier 3 includes deletion, irreversible structural changes, and batches affecting two or more objects.
Use this template:
Destructive Power BI change (Tier 3)
Checkpoint: <confirmed save or TMDL backup and timestamp>
Targets: <every affected object>
Impact: <dependencies and expected behavior change>
Rollback: <exact restore procedure>
Validation: <checks to run afterward>
Reply CONFIRMED to apply only the itemized changes.
Ambient Statement Intercept
Do not execute statements such as "I'm going to...", "we should probably...", "I think I'll...", "we no longer need...", or "at some point...". Treat them as planning context.
What ships with it
2 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.
- 9d ago First seen · 164 lines · 55 tokens per session scan A f179cfa6da81
powerbi-mcp is a skill published in the GitHub repository Kilo-Org/kilo-marketplace (175 stars, last pushed 22d ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,473 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…