custom-agents

Guidance for creating and checking GitHub custom agent files. These Markdown files tell GitHub Copilot how to behave for a whole repository, selected paths, or particular tasks.

In plain words
What is it for?
Use it to define coding standards, security and testing rules, path-specific guidance, or specialized agents such as a test writer or README creator.
Why use it?
It removes the need to remember the required file locations, formats, and settings when giving Copilot repository-specific instructions.

Skill for Claude CodeCodex

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 skills/github/gh-aw/custom-agents
Any agent
npx skills add github/gh-aw --skill custom-agents
Clone the repo
git clone --depth 1 https://github.com/github/gh-aw

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,868 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00018 $0.03868
Opus 5 $0.00009 $0.01934
Sonnet 5 $0.00004 $0.00774
Haiku 4.5 $0.00002 $0.00387

Measured 2d ago against content hash 659af25a21f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

custom-agents scanned grade B with 1 finding 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

tools: ["*"]
.github/skills/custom-agents/SKILL.md · 594 lines

How it starts

The opening of the file, as written. The whole thing — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Custom Agent File Format

Use this reference for the GitHub custom agent file format.

Overview

GitHub Copilot reads custom agent instructions from Markdown files with YAML frontmatter. Use them to define specialized behavior, tool access, and workflows for your repository.

File Locations

Place custom agent files in these locations based on scope:

1. Repository-wide Instructions

  • File: .github/copilot-instructions.md
  • Scope: Applies to all code generation in the repository
  • Use case: General coding standards, security requirements, testing practices

2. Path-specific Instructions

  • Directory: .github/instructions/
  • Pattern: *.instructions.md (e.g., frontend.instructions.md, backend.instructions.md)
  • Scope: Can target specific directories or file patterns using applyTo in frontmatter
  • Use case: Framework-specific guidelines, component-specific rules

3. Custom Agent Profiles

  • Directory: .github/agents/ or .github/copilot/instructions/
  • Pattern: AGENTS.md, *.md (e.g., readme-creator.md, test-writer.md)
  • Scope: Defines specialized agents with specific capabilities and instructions
  • Use case: Task-specific agents (documentation, testing, refactoring)

4. agentic workflow integration

  • Location: Imported via imports field in workflow frontmatter
  • Pattern: Any markdown files under .github/agents/ directory
  • Scope: Custom agent for specific agentic workflow execution
  • Use case: Workflow-specific agent configuration
  • Important: Only one agent file is allowed per workflow

File Format

Basic Structure

# YAML frontmatter (configuration)
name: agent-name
description: Brief description of agent's purpose

# Markdown body (instructions)

Your natural language instructions for the agent go here.

Complete YAML Frontmatter Schema

# Required fields
name: agent-identifier              # Unique identifier for the agent

# Optional descriptive fields
description: >                      # Multi-line description of agent's purpose
  Agent specializing in specific tasks

# Optional instruction fields
prompt: |                          # Freeform instructions (alternative to markdown body)
  Your instructions here

# Optional tool configuration
tools:                             # List of allowed tools for this agent
  - createFile
  - editFiles
  - codeSearch
  - search

# Optional path targeting (for .instructions.md files)
applyTo:                          # Glob patterns for targeted files/directories
  - "src/frontend/**"
  - "**/*.tsx"

# Optional MCP server configuration (enterprise/org only)
mcp-server:                       # External MCP server configuration
  url: https://my-mcp-server.com
  api-key: ${{ secrets.MCPSERVER_API_KEY }}

# Optional settings
settings:                         # Custom runtime or connection settings
  key: value

Read the full file on GitHub · 594 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. 2d ago First seen · 594 lines · 18 tokens per session scan B 659af25a21f5

Subscribe to this mod's changes

custom-agents is a skill published in the GitHub repository github/gh-aw (5,050 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 3,868 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

c-github

Interact with GitHub using the gh CLI and jq. Manage PRs, issues, repositories, and Actions workflows. Make raw API calls with gh api for anything not covered by built-in commands.

daxaur/openpaw · 48 tokens

watch-pr

Watch a GitHub pull request for CI status, reviews, comments, merge conflicts, and terminal states using the gh-watch extension. Use when the user wants to monitor a PR, wait for CI, or track PR progress.

justincampbell/gh-watch · 48 tokens

watch-tag

Watch a GitHub repository for new tags using the gh-watch extension. Use when the user wants to be notified when a tag is created, when a release is cut, or when a tag that includes a specific commit appears (e.g. "tell me when my merge ships in a release").

justincampbell/gh-watch · 62 tokens

watch-branch

Watch a GitHub branch for new commits using the gh-watch extension. Use when the user wants to be notified when new commits are pushed to a branch, monitor main for merges, or track branch activity.

justincampbell/gh-watch · 45 tokens

watch-commit

Watch a GitHub commit for CI status changes using the gh-watch extension. Use when the user wants to monitor a commit's CI checks, wait for a build to finish, or track CI progress on a specific SHA.

justincampbell/gh-watch · 48 tokens

update-architecture-docs

Generate or update the architecture documentation in docs/content/architecture/. Use on "update architecture docs", "generate architecture documentation", "regenerate architecture docs", or after any structural change to the codebase.

AlexSkrypnyk/scaffold · 46 tokens