agentmods.dev

copilot-delegate

copilot-delegate is a skill for Claude Code, Codex from shakestzd/contextune. It costs 66 tokens per session (2,718 once invoked), scanned A, original, MIT.

A delegation skill that sends selected GitHub operations and research tasks to the GitHub Copilot command-line tool. GitHub is a service for hosting and collaborating on code.

In plain words
What is it for?
Use it for GitHub issues, pull requests, repository details, branches, commit history, and research or comparisons of libraries and practices.
Why use it?
It keeps those operations outside the main Claude Code session, preserving that session for decisions and implementation.

Skill for Claude CodeCodex

Part of the contextune plugin — 8 skills, 14 commands, 5 agents, 6 hooks, 1 MCP server shipped together

not rated 5 8mo ago A scan 66 tokens original MIT
View the source file shakestzd/contextune
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/shakestzd/contextune/copilot-delegate
Any agent
npx skills add shakestzd/contextune --skill copilot-delegate
Clone the repo
git clone --depth 1 https://github.com/shakestzd/contextune

Made for: Claude Code, Codex.

Or install contextune, the plugin that ships this one along with the rest of its 8 skills, 14 commands, 5 agents, 6 hooks, 1 MCP server.

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 copilot-delegate

README.md
[![agentmods](https://agentmods.dev/badge/skills/shakestzd/contextune/copilot-delegate.svg)](https://agentmods.dev/skills/shakestzd/contextune/copilot-delegate)
Your own site
<a href="https://agentmods.dev/skills/shakestzd/contextune/copilot-delegate"><img src="https://agentmods.dev/badge/skills/shakestzd/contextune/copilot-delegate.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,718 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00066 $0.02718
Opus 5 $0.00033 $0.01359
Sonnet 5 $0.00013 $0.00544
Haiku 4.5 $0.00007 $0.00272

Measured 4d ago against content hash b5adc134f41d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

copilot-delegate 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 4d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (integration-scripts-v2/init_plan.sh, integration-scripts-v2/setup_worktrees_from_plan.sh, integration-scripts/batch_create_issues.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.

copilot-delegate/SKILL.md · 455 lines

How it starts

The opening of the file, as written. The whole thing — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Delegate

Preserve Claude Code session limits by delegating GitHub operations and research tasks to GitHub Copilot CLI.

Purpose

This skill enables intelligent task delegation to preserve Claude Code's limited session capacity:

  • Pro plan: 10-40 prompts per 5 hours
  • Max 5x: 50-200 prompts per 5 hours
  • Max 20x: 200-800 prompts per 5 hours

By delegating GitHub operations and research to Copilot CLI (which runs in a subprocess), you preserve your main Claude Code session for critical thinking, architecture decisions, and implementation.

When to Use This Skill

Automatic Activation Triggers

The skill activates when Claude detects these keywords in user prompts:

GitHub Operations:

  • "create issue"
  • "list issues"
  • "create PR" / "pull request"
  • "merge PR"
  • "check status"
  • "repo stats"
  • "commit history"
  • "branch operations"

Research Tasks:

  • "research"
  • "compare"
  • "best practices"
  • "which library"
  • "lookup documentation"
  • "what's the best"
  • "evaluate"

Manual Activation

Use when you need to:

  • Perform bulk GitHub operations
  • Research libraries/tools/technologies
  • Analyze documentation
  • Compare multiple options
  • Preserve session capacity for later

Core Workflows

1. GitHub Issue Management

Create a single issue:

./scripts/github_operation.sh create-issue \
  "Fix authentication bug" \
  "Users cannot login with OAuth. Error at auth.ts:42" \
  "bug,priority-high"

List issues:

./scripts/github_operation.sh list-issues . open 20

Query repo:

./scripts/github_operation.sh query \
  "Show last 10 commits with authors and dates"

2. Pull Request Operations

Create PR:

./scripts/github_operation.sh create-pr \
  "Add OAuth authentication" \
  "Implements Auth0 integration. Fixes #123" \
  main \
  feature/oauth

3. Research Tasks

Compare libraries:

./scripts/research_task.sh compare \
  "zustand,jotai,recoil" \
  "bundle-size,DX,performance"

Read the full file on GitHub · 455 lines

Files

What ships with it

28 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.

  1. 4d ago First seen · 455 lines · 66 tokens per session scan A b5adc134f41d

Subscribe to this mod's changes

copilot-delegate is a skill published in the GitHub repository shakestzd/contextune (5 stars, last pushed 8mo ago), licensed MIT. It adds 66 tokens to every session and 2,718 once invoked, about $0.0003 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 2026-08-31.

Cost OptimizationGit and workflowResearchai-assistantautomationclaude-codecontext-engineeringgit-worktrees
Related

Other skills, from other repositories

acceptance-test-authoring

Use when creating or modifying acceptance tests, configuring cucumber-js or behave runners, writing or refactoring step definitions, linting executable Gherkin specs, choosing an acceptance stack, or implementing OpenSpec tasks that involve acceptance tests.

intent-driven-dev/intent-driven-template · 51 tokens

gherkin-authoring

Use when drafting, reviewing, or improving Gherkin, Cucumber scenarios, BDD acceptance criteria, feature examples, Scenario Outlines, Backgrounds, Rules, Doc Strings, Data Tables, tags, or Gherkin embedded in Markdown.

intent-driven-dev/intent-driven-template · 54 tokens

openspec-bulk-apply-change

Use when multiple active OpenSpec changes should be applied concurrently in isolated worktrees with delegated verification and no merge.

intent-driven-dev/intent-driven-template · 30 tokens

architectural-decision-records

Use when documenting, drafting, reviewing, or updating architectural decisions, ADRs, decision logs, tradeoffs, rationale, consequences, alternatives, or architecture decision history.

intent-driven-dev/intent-driven-template · 40 tokens

adversarial-authoring

Use when rules or instructions mention "adversarial-authoring", "adversarial authoring", "must use adversarial-authoring skill", "model council", "cross-model review", or "mixture of models"; coordinates adversarial authoring and review subagents and records council notes.

intent-driven-dev/intent-driven-template · 65 tokens

glossary

Use when authoring or reviewing specs, requirements, design docs, ADRs, tasks, glossary entries, domain terms, technical terms, or wording consistency across artifacts.

intent-driven-dev/intent-driven-template · 36 tokens