copilot-kit: Instructions file for GitHub Copilot

.github/instructions/skill-naming.instructions.md

Skill Naming Conventions is an instructions file for GitHub Copilot from ikcode-dev/copilot-kit. It costs 1,239 tokens per session, scanned A, original, MIT.

A set of naming and structure rules for Agent Skills in the copilot-kit project. An Agent Skill is a reusable capability or multi-step workflow that an AI coding assistant can use.

In plain words
What is it for?
Use it when creating or updating a copilot-kit skill, especially to choose a filename matching the required kit-category-verb-object pattern and structure.
Why use it?
It makes project skills easy to recognize alongside other skills in the VS Code command palette. The required prefix and category format also communicate what each skill covers.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is ikcode-dev/copilot-kit's own configuration. It tells GitHub Copilot how to work on copilot-kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything copilot-kit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ikcode-dev/copilot-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ikcode-dev/copilot-kit/main/.github/instructions/skill-naming.instructions.md
Clone the repo
git clone --depth 1 https://github.com/ikcode-dev/copilot-kit

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 Skill Naming Conventions

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ikcode-dev/copilot-kit/skill-naming/github.svg)](https://agentmods.dev/instructions/ikcode-dev/copilot-kit/skill-naming)
Your own site
<a href="https://agentmods.dev/instructions/ikcode-dev/copilot-kit/skill-naming"><img src="https://agentmods.dev/badge/instructions/ikcode-dev/copilot-kit/skill-naming/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Skill Naming Conventions

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ikcode-dev/copilot-kit/skill-naming"><img src="https://agentmods.dev/badge/instructions/ikcode-dev/copilot-kit/skill-naming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,239 This file is loaded in full into every session.
When invoked 1,239 The same file — it is already loaded in full.
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 $0.01239 $0.01239
Opus 5.5 $0.00496 $0.00496
Sonnet 5.5 $0.00248 $0.00248
Haiku 4.5 $0.00124 $0.00124

Measured 2mo ago against content hash a0f336651d00, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Skill Naming Conventions 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 2mo 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/skill-naming.instructions.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Naming Conventions for copilot-kit

These conventions ensure skills from this repository are instantly identifiable when mixed with project-specific skills in the VS Code / command palette.

Naming Pattern

All skills in this repository must follow:

kit-{category}-{verb}-{object}
Segment Purpose Examples
kit- Origin prefix — identifies the skill as coming from copilot-kit Always kit-
{category} Domain grouping copilot, sdd
{verb} Action the skill performs create, check, implement, review
{object} Target of the action agent, skill, hook, spec, conformance

Why kit-?

  • ck- — too cryptic, not recognizable at a glance
  • copilot-kit- — too long, wastes the 64-char name limit
  • kit- — 4 chars, filters all copilot-kit skills together when typing /kit-

Categories

Category Scope
copilot Skills related to Copilot customization (agents, skills, hooks, instructions, prompts)
sdd Skills related to Spec-Driven Development workflows (specs, conformance checks, implementation)

New categories follow the same pattern: short, lowercase, hyphenated.

Directory Structure

The name field in SKILL.md frontmatter must match the parent directory name. Intermediate grouping directories (copilot/, sdd/) are for filesystem organization only:

.github/skills/
  copilot/
    kit-copilot-create-agent/SKILL.md
    kit-copilot-create-skill/SKILL.md
  sdd/
    kit-sdd-create-spec/SKILL.md
    kit-sdd-check-conformance/SKILL.md

SKILL.md Frontmatter Requirements

---
name: kit-{category}-{verb}-{object}    # must match directory name
description: "A skill that [verb]s [object] for [context]. Use when [trigger scenario]."
argument-hint: Describe what input to provide
user-invocable: true
disable-model-invocation: false
---
  • description should explain both what the skill does and when to use it so Copilot's progressive disclosure loads it automatically at the right time.
  • Keep name under 64 characters (the spec maximum).

Read the full file on GitHub · 121 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. 2mo ago First seen · 121 lines · 1,239 tokens per session scan A a0f336651d00

Subscribe to this mod's changes

Skill Naming Conventions is an instructions file published in the GitHub repository ikcode-dev/copilot-kit (29 stars, last pushed 7mo ago), licensed MIT. It adds 1,239 tokens to every session, about $0.0050 per session on Opus 5.5. 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.

Related

Skill Naming Conventions compared with instructions from other repositories

Skill Naming Conventions next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Skill Naming Conventionsikcode-dev/copilot-kitInstructions file297mo agoMITA1,239GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode