Agent Naming Conventions

A set of rules for naming and grouping custom agents in copilot-kit, a toolkit for creating coding agents. It uses names that show an agent’s origin, subject area, and role.

In plain words
What is it for?
Use it when adding or reviewing copilot-kit agents and deciding names such as category, role, and optional seniority or planning labels.
Why use it?
It prevents custom agents from becoming hard to identify in the VS Code agent picker. Consistent names also distinguish agents from skills, which perform specific actions.

Instructions file for GitHub Copilot

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/ikcode-dev/copilot-kit/agent-naming
Clone the repo
git clone --depth 1 https://github.com/ikcode-dev/copilot-kit

Made for: GitHub Copilot.

Per session 1,270 This file is loaded in full into every session.
When invoked 1,270 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 $0.01270 $0.01270
Opus 5 $0.00635 $0.00635
Sonnet 5 $0.00254 $0.00254
Haiku 4.5 $0.00127 $0.00127

Measured yesterday against content hash 9b2c1654b65b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Agent 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 yesterday.

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/agent-naming.instructions.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Naming Conventions for copilot-kit

These conventions ensure agents from this repository are instantly identifiable when mixed with project-specific agents in the VS Code agent picker.

Naming Pattern

All agents in this repository must follow:

kit-{category}-{role}(-{qualifier})*
Segment Purpose Examples
kit- Origin prefix — identifies the agent as coming from copilot-kit Always kit-
{category} Domain grouping copilot, sdd, backend
{role} The persona or role the agent fulfills architect, expert, engineer
(-{qualifier})* Optional qualifier for specificity -senior, -planner

Why kit-?

  • ck- — too cryptic, not recognizable at a glance
  • copilot-kit- — too long, wastes space in the agent picker
  • kit- — 4 chars, groups all copilot-kit agents together when browsing

Agent naming is role-oriented, not action-oriented

Skills use kit-{category}-{verb}-{object} because they perform actions. Agents use kit-{category}-{role} because they represent personas with expertise, tools, and behavioral guidelines.

Categories

Category Scope
copilot Agents related to Copilot customization and configuration workflows
sdd Agents related to Spec-Driven Development workflows
backend Agents focused on backend / server-side engineering

New categories follow the same pattern: short, lowercase, hyphenated. A category can be domain-specific (e.g., frontend, devops) or workflow-specific (e.g., sdd, copilot).

Filename Convention

The filename must follow:

{agent-name}.agent.md

Where {agent-name} matches the naming pattern. All agents live directly in .github/agents/ (flat structure, no subdirectories):

.github/agents/
  kit-copilot-engineering-team.agent.md
  kit-sdd-expert.agent.md
  kit-backend-engineer.agent.md

Agent Frontmatter Requirements

---
description: >-                          # be specific — this drives agent selection
  A brief sentence describing the agent's expertise and purpose.
  When/why to use this agent.
argument-hint: Describe what input to provide
tools: [...]                             # tools the agent has access to
---

Read the full file on GitHub · 137 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. yesterday First seen · 137 lines · 1,270 tokens per session scan A 9b2c1654b65b

Subscribe to this mod's changes

Agent Naming Conventions is an instructions file published in the GitHub repository ikcode-dev/copilot-kit (29 stars, last pushed 5mo ago), licensed MIT. It adds 1,270 tokens to every session, about $0.0064 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.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit 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.

github/spec-kit · 7,040 tokens

langchain AGENTS.md

Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens