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/luccapinto/agentic-data-kit/agents-mdgit clone --depth 1 https://github.com/luccapinto/agentic-data-kitWhat 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 | $0.00594 | $0.00594 |
| Opus 5 | $0.00297 | $0.00297 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
agentic-data-kit AGENTS.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 2d 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.
This is a copy
100% identical to agentic-data-kit copilot-instructions.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Data Kit — Operating Rules
Global behavior for AI assistants working in this repository. Keep it short on purpose: every token here competes for the model's attention, so this file holds only high-signal, data-specific rules — not things a capable model already does well.
Language
- Write all code, identifiers, and artifacts in English.
- Respond to the user in the language they write in (Portuguese in, Portuguese out).
How to work
- Route to a specialist. Pick the agent whose domain fits the request and briefly say which one you're applying (e.g. "Applying @data-engineer"). For cross-domain requests, split the work across agents and merge the results.
- Skills activate themselves. Every skill declares when it applies in its
description. When a request matches it — "document this", "edit this Power BI model" — load thatSKILL.mdon demand, with or without an agent involved. Skills do not require an owning agent; theskills:field on an agent is only a hint. Don't preload every file in a folder. - Creating or changing an agent/skill/workflow? Load the
creating-agents-and-skillsskill first — it decides whether to build an agent, a skill, or nothing, and keeps every installed tool folder (.agent,.claude,.github,.opencode,.cursor) in sync. - Clarify only when genuinely blocked. If the request is ambiguous enough that you'd likely build the wrong thing, ask. Otherwise state your assumptions and proceed.
Data engineering principles (always apply)
- Idempotency: Pipelines must be safely re-runnable. Prefer
MERGE/OVERWRITEover blindINSERT. Re-running a window yields the same result. - Write-Audit-Publish: Write to staging → run quality checks → publish only if they pass.
- Check downstream impact before changing any schema, contract, or shared model.
- Never hardcode secrets or PII. Use secret managers; mask PII at the Silver layer.
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.
- 2d ago First seen · 46 lines · 594 tokens per session scan A c48def355de3
agentic-data-kit AGENTS.md is an instructions file published in the GitHub repository luccapinto/agentic-data-kit (7 stars, last pushed 1mo ago), licensed MIT. It adds 594 tokens to every session, about $0.0030 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agentic-data-kit copilot-instructions.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
dbt-mcp CLAUDE.md
Instructions for dbt-labs/dbt-mcp, covering claude.md, project overview, key paths, tool architecture and mcp apps (tools with interactive ui).
dbt-mcp AGENTS.md
Instructions for dbt-labs/dbt-mcp: See CLAUDE.md for additional context and instructions.
apm python.instructions.md
Python development guidelines.
mcp-server-excel coverage-prevention-strategy.instructions.md
Instructions for sbroenne/mcp-server-excel, covering generated surface coverage, contract change workflow, required checks and common incomplete changes.
mcp-server-excel mcp-llm-guidance.instructions.md
Instructions for sbroenne/mcp-server-excel, a project described as: Automate real Microsoft Excel with AI via MCP Server or CLI — Power Query, DAX, VBA, PivotTables, charts, and 326 operations.
goldenmatch CLAUDE.md
Instructions for benseverndev-oss/goldenmatch, covering golden suite monorepo, typescript: pnpm + turborepo (post-2026-05-02 fold), ci (.github/workflows/ci.yml), ci path filters (post-2026-05-06, pr #89) and merge queue: main serializes merges fifo (since 2026-06-15).