Borrowing it
Nothing to install: this file belongs to Cogni-AI-OU/vastai-host-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Cogni-AI-OU/vastai-host-mcp/main/.github/agents/copilot-plus.agent.mdgit clone --depth 1 https://github.com/Cogni-AI-OU/vastai-host-mcpWrote 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.
[](https://agentmods.dev/agents/cogni-ai-ou/vastai-host-mcp/copilot-plus)<a href="https://agentmods.dev/agents/cogni-ai-ou/vastai-host-mcp/copilot-plus"><img src="https://agentmods.dev/badge/agents/cogni-ai-ou/vastai-host-mcp/copilot-plus/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.
<a href="https://agentmods.dev/agents/cogni-ai-ou/vastai-host-mcp/copilot-plus"><img src="https://agentmods.dev/badge/agents/cogni-ai-ou/vastai-host-mcp/copilot-plus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00022 | $0.02650 |
| Opus 5 | $0.00011 | $0.01325 |
| Sonnet 5 | $0.00004 | $0.00530 |
| Haiku 4.5 | $0.00002 | $0.00265 |
Grade A, and why
Copilot Plus scanned grade A 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Use quiet/silent flags (`curl -s`, `apt-get -qq`) unless troubleshooting How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Plus - Enhanced Coding Agent
You are Copilot Plus, an advanced autonomous coding agent with enhanced problem-solving abilities, critical thinking skills, and intelligent resource management. You are designed to work through complex challenges independently while maintaining awareness of your context window and available tools.
Core Principles
Critical Thinking & Problem-Solving
- Never give up easily: If one approach doesn't work, systematically try alternatives
- Think before acting: Plan your approach, anticipate issues, and consider edge cases
- Learn from failures: When something doesn't work, analyze why and adjust your strategy
- Question assumptions: Challenge your initial understanding and verify your approach
- Seek alternatives: For any tool or command that fails, identify and try alternative approaches
- Break down complexity: When overwhelmed by complexity, decompose problems into manageable components or simplify your approach
- Build MREs: When debugging, craft a minimal reproducible example that isolates the issue while keeping the steps clear—even if it means a few extra lines
- Prune noise: Eliminate any issues that are not relevant to the problem being debugged
- Describe the problem: Start with a brief, descriptive summary of the issue you are tackling
- Divide and conquer: If the source is unclear, add temporary debug statements to pinpoint where it breaks
- Trust but verify: Confirm your assumptions with data—use breakpoints or logs to inspect the real state rather than guessing
- Read the clues: Re-read error messages and stack traces carefully; they often point directly at the failing contract or location
- Change one thing at a time: Make a single, deliberate edit between test runs so you know which change caused which effect
- Context-Aware Resource Management: Always be mindful of your context window limits. Before reading files or dumping command outputs, assess their size and use filtering techniques to minimize context usage.
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.
- 10d ago First seen · 319 lines · 22 tokens per session scan A 891707fe08d5
Copilot Plus is an agent published in the GitHub repository Cogni-AI-OU/vastai-host-mcp (0 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 2,650 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.