agentmods.dev

drift drift-prompt-engineering.instructions.md

drift drift-prompt-engineering.instructions.md is an instructions file for GitHub Copilot from mick-gsk/drift. It costs 1,069 tokens per session, scanned A, original, MIT.

A set of German-language rules for creating, improving, and reviewing prompts, instructions, skills, agents, and Copilot customizations in the Drift workspace.

In plain words
What is it for?
It guides prompt structure, file scope, shared text reuse, output agreements, and checks against making up information.
Why use it?
It helps keep prompt files focused, reusable, discoverable, and less likely to produce unsupported answers.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot chat mode or prompt.

not rated 14 1mo ago A scan 1,069 tokens original MIT
View the source file mick-gsk/drift mick-gsk.github.io
Install

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.

agentmods
npx agentmods add instructions/mick-gsk/drift/drift-prompt-engineering
Clone the repo
git clone --depth 1 https://github.com/mick-gsk/drift

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for drift drift-prompt-engineering.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mick-gsk/drift/drift-prompt-engineering.svg)](https://agentmods.dev/instructions/mick-gsk/drift/drift-prompt-engineering)
Your own site
<a href="https://agentmods.dev/instructions/mick-gsk/drift/drift-prompt-engineering"><img src="https://agentmods.dev/badge/instructions/mick-gsk/drift/drift-prompt-engineering.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,069 This file is loaded in full into every session.
When invoked 1,069 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01069 $0.01069
Opus 5 $0.00535 $0.00535
Sonnet 5 $0.00214 $0.00214
Haiku 4.5 $0.00107 $0.00107

Measured 5d ago against content hash 4c4fbcdef316, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

drift drift-prompt-engineering.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 5d 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.

.github/instructions/drift-prompt-engineering.instructions.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drift Prompt Engineering

Diese Instruction gilt fuer Prompt-Arbeit im Drift-Workspace. Sie ergänzt den Prompt-Engineering-Modus aus .github/copilot-instructions.md und ist nicht die Single Source of Truth fuer Primitive-Wahl, Policy-Gate oder Grundregeln.

Wenn eine Regel bereits in .github/copilot-instructions.md, .github/instructions/drift-policy.instructions.md, .github/prompts/_partials/*.md oder im Skill .github/skills/drift-agent-prompt-authoring/SKILL.md steht, wird sie referenziert und nicht erneut ausformuliert.

Wenn die Aufgabe primär einen neuen oder geänderten Workflow-Prompt unter .github/prompts/ betrifft, ist der Skill .github/skills/drift-agent-prompt-authoring/SKILL.md die erste operative Referenz. Diese Instruction liefert nur die zusaetzlichen Dateiregeln.

Diese Instruction ergänzt das PFLICHT-GATE aus .github/instructions/drift-policy.instructions.md. Prompt-Arbeit ist nur zulaessig, wenn sie Erkenntnis, Vergleichbarkeit, Einfuehrbarkeit oder Signalqualitaet verbessert — nicht wenn sie nur mehr Text produziert.

Zusaetzliche Dateiregeln

  • description muss den Task-Typ, den Trigger und den Scope benennen. Beispiele: "Prompt schaerfen", "Instruction erstellen", "Skill reviewen", "Agent konfigurieren".
  • applyTo wird nur gesetzt, wenn Dateimatching wirklich gewuenscht ist; on-demand-only Regeln bleiben ohne applyTo.
  • Mehrere applyTo-Patterns werden als Array gepflegt, nicht als unleserliche Sammelzeile.
  • Datei- oder Ordnerregeln gehoeren in *.instructions.md, nicht in copilot-instructions.md.
  • Prompt-spezifische Arbeitsablaeufe gehoeren in *.prompt.md, nicht in Instructions.
  • Wiederverwendbare Operator-Abläufe mit Ein-/Ausstiegslogik gehoeren in SKILL.md.
  • *.agent.md ist nur zulaessig, wenn Kontext-Isolation oder andere Tool-Grenzen gebraucht werden.

Zusatzregeln fuer Prompt-Artefakte

  • Prompts unter .github/prompts/ benennen Ziel, Inputs, Phasen, Artefakte und Bewertungslogik explizit und verweisen fuer Standards auf Shared Partials.
  • Instructions unter .github/instructions/ bleiben kurz, datei- oder task-spezifisch und enthalten keine zweite Policy-Ebene.
  • Skills unter .github/skills/ benennen in der description klar, wann sie genutzt werden und wann nicht.
  • Field-Test-Prompts benennen immer mick-gsk/drift als Ziel fuer Findings und Issues.
  • Neue Regeln werden erst geschrieben, nachdem geprueft wurde, dass sie nicht schon in einer Single Source of Truth existieren.

Read the full file on GitHub · 83 lines

Changes

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.

  1. 5d ago First seen · 83 lines · 1,069 tokens per session scan A 4c4fbcdef316

Subscribe to this mod's changes

drift drift-prompt-engineering.instructions.md is an instructions file published in the GitHub repository mick-gsk/drift (14 stars, last pushed 1mo ago), licensed MIT. It adds 1,069 tokens to every session, about $0.0053 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.

Building agentsData and AIPromptingai-generated-codearchitectureclicode-qualitycopilot
Related

Other instructions, from other repositories

apex-accelerator vendor-prompting.instructions.md

Vendor prompting best-practice rules for Anthropic Claude and OpenAI GPT-5.6-Terra agents and prompts. Each rule cites a rule ID in the vendor-prompting skill rules.json registry. Validator: npm run lint:vendor-prompting.

jonathan-vella/apex-accelerator · 1,488 tokens

llm-ide-rules AGENTS.md

AGENTS.md instructions for iloveitaly/llm-ide-rules, covering code comments, important workflow rules, alembic migrations, default content for new non-nullable columns and 1. add the column as nullable (no default needed).

iloveitaly/llm-ide-rules · 6,061 tokens

llm-ide-rules pytest-integration-tests.instructions.md

Instructions for iloveitaly/llm-ide-rules, covering pytest integration tests and example integration test.

iloveitaly/llm-ide-rules · 1,299 tokens

llm-ide-rules copilot-instructions.md

Copilot instructions for iloveitaly/llm-ide-rules, covering code comments and important workflow rules.

iloveitaly/llm-ide-rules · 977 tokens

llm-ide-rules python-app.instructions.md

Instructions for iloveitaly/llm-ide-rules, covering python app, factories and database & orm.

iloveitaly/llm-ide-rules · 1,286 tokens

llm-ide-rules react.instructions.md

Instructions for iloveitaly/llm-ide-rules, covering react, mock data, react hook form and styling.

iloveitaly/llm-ide-rules · 1,033 tokens