What is convert-to-copilot?

A conversion workflow turns a Claude Code agent, its launch command and its skills into one GitHub Copilot agent file with supporting context and decision files. GitHub Copilot agents are configured assistants that work inside GitHub's development tools.

It is for creating `.github/agents` output and `.copilot_utils` files that separate the agent's workflow, reference information and branching decisions.

It removes the need to translate the agent structure and supporting instructions manually between the two systems.

convert-to-copilot — Skill for Claude Code by endorphin-ai

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 endorphin-ai/hasbrains-agent-kit --skill convert-to-copilot

Clone the repo

git clone --depth 1 https://github.com/endorphin-ai/hasbrains-agent-kit

Made for: Claude Code.

Or install agent-engineering, the plugin that ships this one along with the rest of its 7 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/endorphin-ai/hasbrains-agent-kit/convert-to-copilot/github.svg)](https://agentmods.dev/skills/endorphin-ai/hasbrains-agent-kit/convert-to-copilot)

Your own site

<a href="https://agentmods.dev/skills/endorphin-ai/hasbrains-agent-kit/convert-to-copilot"><img src="https://agentmods.dev/badge/skills/endorphin-ai/hasbrains-agent-kit/convert-to-copilot/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/endorphin-ai/hasbrains-agent-kit/convert-to-copilot"><img src="https://agentmods.dev/badge/skills/endorphin-ai/hasbrains-agent-kit/convert-to-copilot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,671 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.

Model	Per session	Once invoked
Fable 5.1	$0.00103	$0.02671
Opus 5.5	$0.00041	$0.01068
Sonnet 5.5	$0.00021	$0.00534
Haiku 4.5	$0.00010	$0.00267

Measured 1mo ago against content hash 688b86a89563, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

convert-to-copilot 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 1mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/claude-to-copilot.sh, scripts/convert-agents.sh, scripts/copilot-to-claude.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

agent-engineering/skills/convert-to-copilot/SKILL.md · 240 lines

How it starts

The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Convert Claude Code → GitHub Copilot Agent

Converts a Claude Code agent + command + skills into a .github/agents/*.agent.md with supporting files in a per-agent .copilot_utils/{agent_name}/ directory.

Canonical Output Structure

.github/
└── agents/
    └── {agent_name}.agent.md       ← single merged file (agent + command)

.copilot_utils/
└── {agent_name}/
    ├── context/                    ← WHAT to use (knowledge, conventions, reference)
    │   └── {skill}.md
    └── trees/                      ← HOW to decide (branching, if/else logic)
        └── {skill}.md

External guide: https://github.com/endorphin-ai/vs-code-copilot-agents/blob/main/COPILOT_AGENTS_GUIDE.md

Three-File Separation Principle

Every file has exactly one role:

File Type	Location	Contains	Example
Agent	`.github/agents/`	WHAT to do — workflow, phases, orchestration	"Read file, apply tree, validate, create output"
Tree	`.copilot_utils/{agent_name}/trees/`	HOW to decide — if/else branching logic	"If label contains X → use path Y"
Context	`.copilot_utils/{agent_name}/context/`	WHAT to use — reference info, patterns, rules	"Available scaffolds: A, B, C"

NEVER embed knowledge or decision logic in the agent body. Reference files instead:

Decisions → **Apply tree:** .copilot_utils/{agent_name}/trees/{file}.md
Reference → **Reference:** .copilot_utils/{agent_name}/context/{file}.md

Variables

{agent_file}      = $ARGUMENTS (path to Claude agent .md file)
{command_file}    = (path to Claude command .md — ask if not provided)
{agent_name}      = (extracted from agent frontmatter `name` field)
{output_agent}    = .github/agents/{agent_name}.agent.md
{output_dir}      = .copilot_utils/{agent_name}
{trees_dir}       = .copilot_utils/{agent_name}/trees
{knowledge_dir}   = .copilot_utils/{agent_name}/context
{output_folder}   = .copilot-convert-results

Read the full file on GitHub · 240 lines

Files

What ships with it

13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 240 lines · 103 tokens per session scan A 688b86a89563

Subscribe to this mod's changes

convert-to-copilot is a skill published in the GitHub repository endorphin-ai/hasbrains-agent-kit (9 stars, last pushed 12d ago), licensed MIT. It adds 103 tokens to every session and 2,671 once invoked, about $0.0004 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 2026-09-23.

Building agents Claude Code agent-skills agentic-engineering anthropic claude claude-code-agents

hydra

Multi-agent orchestration framework for Claude Code. Automatically delegates tasks to cheaper, faster sub-agents (Haiku, Sonnet) while maintaining Opus-level quality through verification. Use when working on any coding task — Hydra activates automatically to route file exploration, test running, documentation, code…

AR6420/Hail_Hydra · 83 tokens

rfc

Manage architecture RFCs: create, review, list, update, and transition status. Use when user mentions "RFC", "technical proposal", "architecture proposal", or wants to draft, review, list, update, or change status of RFCs.

joaquimscosta/arkhe-claude-plugins · 53 tokens

cleaning-up-branches

Deletes merged git branches (local and remote) and flags stale unmerged branches for manual review. Use when user mentions "cleanup branches", "delete merged branches", "prune old branches", "remove stale branches", "branch cleanup", or runs /cleanup-branches command.

joaquimscosta/arkhe-claude-plugins · 61 tokens

prototype

Rapid UI prototyping — generates 3 visually distinct HTML/CSS components from a text prompt and serves them in a live browser gallery. Use when user runs /prototype, asks to "prototype a UI", "mock up a component", "generate HTML mockups", "create UI variations", "design exploration", "quick UI concept", or wants to…

joaquimscosta/arkhe-claude-plugins · 118 tokens

quality-stack

Scan a project to detect configured quality and testing tools across JVM (Gradle/Maven), Android (AGP/Compose/KMP), Node.js/TypeScript, and Python ecosystems. Cross-reference against research-backed recommendations and assist with setup. Auto-detects project type(s) including monorepos with mixed ecosystems. Use when…

joaquimscosta/arkhe-claude-plugins · 148 tokens

doc-freshness

Detect documentation drift, stale references, and cross-document inconsistencies in any project. Scans for code-doc drift (API/function changes not reflected in docs), cross-doc drift (conflicting information across documents), and stale references (broken links, deleted files, outdated versions). Use when checking…

joaquimscosta/arkhe-claude-plugins · 107 tokens