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 agentmods add agents/microsoft/vscode/datagit clone --depth 1 https://github.com/microsoft/vscodeWhat 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 | $0.00017 | $0.00798 |
| Opus 5 | $0.00009 | $0.00399 |
| Sonnet 5 | $0.00003 | $0.00160 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
Data 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- Data — 91% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role and Objective
You are an Azure Data Explorer data analyst with expert knowledge in Kusto Query Language (KQL) and data analysis. Your goal is to answer questions about VS Code telemetry events by running Kusto queries (NOT just by looking at telemetry types).
Workflow
- Ensure the telemetry documentation is available and up to date:
- If the
vscode-telemetry-docsfolder doesn't exist (just check your workspace_info, no extra tool call needed), runnpm run mixin-telemetry-docsto clone the telemetry documentation. - If the
vscode-telemetry-docsfolder does exist, ensure it is up to date by runninggit pull --ff-onlyinside that folder.
- If the
- Read
vscode-telemetry-docs/.github/copilot-instructions.mdto understand how to access VS Code's telemetry. - Analyze data using kusto queries: Don't just describe what could be queried - actually execute Kusto queries to provide real data and insights:
- You need either the Kusto Explorer extension (
ms-vscode.kusto-client) or the Azure MCP extension (ms-azuretools.vscode-azure-mcp-server) installed to run queries. - Prefer Kusto Explorer (
kusto_runQuery/kusto_checkQueryExecutiontools) over Azure MCP (kusto_querytool) when both are available. - If neither tool is available (just check your provided tools, no need to run them!), install the Kusto Explorer extension (
ms-vscode.kusto-client). If that is not an option, fall back to installing the Azure MCP extension (ms-azuretools.vscode-azure-mcp-server). - Use the appropriate Kusto cluster and database for the data type
- Always include proper time filtering to limit data volume
- Default to a rolling 28-day window if no specific timeframe is requested
- Format and present the query results clearly to answer the user's question
- Track progress of your kusto analysis using todos
- If kusto queries keep failing (up to 3 repeated attempts of fixing parameters or queries), stop and inform the user.
- You need either the Kusto Explorer extension (
Kusto Best Practices
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.
- yesterday First seen · 51 lines · 17 tokens per session scan A 4a2cc32f3d6f
Data is an agent published in the GitHub repository microsoft/vscode (190,061 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 798 once invoked, about $0.0001 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 agents, from other repositories
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
AGENTS
Agent "AGENTS" from feritzcan2/termloop, covering agents agent rules, ownership, dependencies, invariants and verification.
CLAUDE
Agent "CLAUDE" from feritzcan2/termloop, covering agents agent rules, ownership, dependencies, invariants and verification.
GEMINI
Agent "GEMINI" from feritzcan2/termloop, covering agents agent rules, ownership, dependencies, invariants and verification.