create-instructions

create-instructions is a skill for Claude Code from microsoft/vscode. It costs 19 tokens per session (287 once invoked), scanned A, original, MIT.

A guide for creating an instructions file that records project rules and coding conventions in Markdown. The file can apply to the whole project or to selected files.

In plain words
What is it for?
Use it to define naming rules, coding patterns, documentation styles, or technology-specific guidance.
Why use it?
It keeps the agent's behaviour consistent without repeating the same preferences and corrections in every request.

Skill for Claude Code ✓ vendor

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents.

Good fit Use it to define naming rules, coding patterns, documentation styles, or technology-specific…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/microsoft/vscode/create-instructions
About the project

Visual Studio Code is a code editor that supports editing, navigating, understanding, debugging, and extending software projects. Developers use it for the edit-build-debug cycle, and the catalogue add-ons provide skills, instructions, and agents for working within the editor.

microsoft/vscode · 190,932 stars · on GitHub · code.visualstudio.com

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.

Any agent
npx skills add microsoft/vscode --skill create-instructions
Clone the repo
git clone --depth 1 https://github.com/microsoft/vscode

Made for: Claude Code.

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 create-instructions

README.md
[![agentmods](https://agentmods.dev/badge/skills/microsoft/vscode/create-instructions.svg)](https://agentmods.dev/skills/microsoft/vscode/create-instructions)
Your own site
<a href="https://agentmods.dev/skills/microsoft/vscode/create-instructions"><img src="https://agentmods.dev/badge/skills/microsoft/vscode/create-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 287 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00019 $0.00287
Opus 5 $0.00010 $0.00143
Sonnet 5 $0.00004 $0.00057
Haiku 4.5 $0.00002 $0.00029

Measured 3d ago against content hash 590f0d748a0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

create-instructions 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 3d 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.

extensions/copilot/assets/prompts/skills/create-instructions/SKILL.md · 31 lines

What it actually says

Related skill: agent-customization. Load and follow instructions.md for template and principles.

Guide the user to create an instructions file.

Extract from Conversation

First, review the conversation history. If the user has been correcting the agent's output or asking for specific patterns (e.g., "always use X", "never do Y", "follow this style"), generalize that into a persistent instruction. Extract:

  • Corrections or preferences mentioned during the conversation
  • Coding patterns the user enforced or requested
  • Project-specific conventions referenced

Clarify if Needed

If no clear rule emerges from the conversation, clarify:

  • Should this apply everywhere or only to specific files?
  • Which technologies or file types are affected?
  • Is this a hard rule or a preference?

Explore the codebase using subagents if you need more context.

Iterate

  1. Draft the instruction and save it.
  2. Identify the most ambiguous or weak parts and ask about those.
  3. Once finalized, summarize what the instruction enforces, suggest example prompts to see it in action, and propose related customizations to create next.

Remember to follow the agent-customization guidelines to create highly effective instructions.

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. 3d ago First seen · 31 lines · 19 tokens per session scan A 590f0d748a0c

Subscribe to this mod's changes

create-instructions is a skill published in the GitHub repository microsoft/vscode (190,932 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 287 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 2026-09-03.