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 instructions/tyrrestrup/ssis_adf_agent/copilot-instructionsgit clone --depth 1 https://github.com/tyrrestrup/ssis_adf_agentWrote 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/instructions/tyrrestrup/ssis_adf_agent/copilot-instructions)<a href="https://agentmods.dev/instructions/tyrrestrup/ssis_adf_agent/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/tyrrestrup/ssis_adf_agent/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.01255 | $0.01255 |
| Opus 5 | $0.00628 | $0.00628 |
| Sonnet 5 | $0.00251 | $0.00251 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
ssis_adf_agent copilot-instructions.md 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SSIS → ADF Conversion Agent — Copilot Domain Knowledge
Project Overview
This project exposes an MCP server (ssis-adf-agent) that reads SSIS packages (.dtsx)
and converts them to Azure Data Factory (ADF) JSON artifacts. Five tools are available
via the MCP server; use them in the order that makes sense for the task.
MCP Tools Available
| Tool | Purpose |
|---|---|
scan_ssis_packages |
Discover .dtsx files from local path, Git repo, or SQL Server |
analyze_ssis_package |
Complexity score, gap analysis, and dependency order for one package |
convert_ssis_package |
Full conversion to ADF JSON (pipeline, linked services, datasets, data flows, triggers) |
validate_adf_artifacts |
Structural validation of generated JSON before deploying |
deploy_to_adf |
Push artifacts to Azure Data Factory via SDK |
SSIS Component Mapping
| SSIS Component | ADF Equivalent | Notes |
|---|---|---|
| Execute SQL Task | Stored Procedure / Script / Lookup Activity | Depends on ResultSetType and SQL pattern |
| Data Flow Task (simple) | Copy Activity | Single source → single destination, no transformations |
| Data Flow Task (complex) | Execute Data Flow Activity (Mapping Data Flow) | Multiple sources, transformations, or fanout |
| Execute Package Task | Execute Pipeline Activity | Child pipeline must also be converted |
| Script Task (C# / VB) | Azure Function Activity | Stub generated at stubs/<FunctionName>/__init__.py; requires manual porting |
| ForEach Loop Container | ForEach Activity | Expression varies by enumerator type |
| For Loop Container | SetVariable (init) + Until Activity + SetVariable (increment) | Condition logic is inverted |
| Sequence Container | Flattened into parent with dependsOn chaining | No ADF equivalent |
| File System Task | Copy Activity (Azure paths) or Web Activity → Azure Function | Local paths need Azure-path substitution |
| Execute Process Task | Web Activity → Azure Function | Manual: wrap process call in Function |
| FTP Task | FTP connector via Copy Activity | Requires FTP linked service |
| Send Mail Task | Logic App / Web Activity | No native ADF equivalent |
| Event Handler (OnError) | Pipeline fails path / error handling | Converted to sub-pipeline reference |
| Event Handler (OnPostExecute) | Succeeded dependency path | Converted to sub-pipeline reference |
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 · 129 lines · 1,255 tokens per session scan A 864998069e55
ssis_adf_agent copilot-instructions.md is an instructions file published in the GitHub repository tyrrestrup/ssis_adf_agent (0 stars, last pushed 5mo ago), licensed MIT. It adds 1,255 tokens to every session, about $0.0063 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 2026-08-31.
Other instructions, from other repositories
skypilot CLAUDE.md
Claude Code instructions for skypilot-org/skypilot, a project described as: The AI Compute Platform for frontier teams. SkyPilot turns fragmented AI compute into one AI supercomputer, so frontier AI teams build custom intelligence faster.
sample-sagemaker-agentic-model-deployment AGENTS.md
AGENTS.md instructions for aws-samples/sample-sagemaker-agentic-model-deployment, a project described as: Agent-driven staging, deployment, benchmarking, and optimization of open-weight models on Amazon SageMaker AI using portable SKILL.md contracts.
data-ingestion-github-to-snowflake CLAUDE.md
Claude Code instructions for surfalytics/data-ingestion-github-to-snowflake, covering claude.md, project context, cloudformation templates, deploy iam stack (required first) and deploy batch stack (requires iam stack to exist).
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.