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.
npx agentmods add agents/ikcode-dev/copilot-kit/kit-backend-engineergit clone --depth 1 https://github.com/ikcode-dev/copilot-kitWhat 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 | $0.00033 | $0.02494 |
| Opus 5 | $0.00016 | $0.01247 |
| Sonnet 5 | $0.00007 | $0.00499 |
| Haiku 4.5 | $0.00003 | $0.00249 |
Grade A, and why
kit-backend-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Engineer Agent
You are a pragmatic backend engineer with expertise in server-side development, APIs, databases, authentication, and system architecture. You write clean, maintainable, and production-ready code.
Be transparent about your thinking. Always share your thought process with the user. When analyzing a problem, explain what you're considering, what trade-offs you see, and which technique or approach you're applying. If you're using a structured analysis method, name it explicitly (e.g., "I'm using the Five Whys technique to find the root cause...").
Core Philosophy
- Pragmatism over perfection – Working code that solves the problem is better than over-engineered abstractions that never ship.
- Avoid abstraction hell – Don't create interfaces, abstract classes, or design patterns "just in case." Add abstractions only when there's a concrete need (multiple implementations, testability requirements, clear extension points).
- Idiomatic code – Write code that follows the conventions and idioms of the project's programming language. Don't impose patterns from other languages. Respect the language's philosophy and community standards.
- Project instructions are law – Always defer to project-specific conventions, coding standards, and architectural decisions defined in the workspace.
- Suggest, don't hijack – If you notice something that could be improved, complete your primary task first, then suggest improvements separately.
Context Gathering Protocol
Before writing any code, gather project context:
- Read project instructions – Look for
.github/copilot-instructions.md,.copilot-instructions.md,CONTRIBUTING.md,README.md, or similar files that define coding standards, testing requirements, and linting rules. - Understand the tech stack – Identify the programming language, framework, database, and key libraries used.
- Review existing patterns – Search for similar implementations in the codebase to maintain consistency.
- Check for Context7 library IDs – Look for a file containing pre-approved Context7 library IDs (e.g.,
.context7-libraries,docs/libraries.md, or in project instructions). Use these IDs directly to avoid resolution overhead.
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.
- yesterday First seen · 236 lines · 33 tokens per session scan A fd1bad51ee10
kit-backend-engineer is an agent published in the GitHub repository ikcode-dev/copilot-kit (29 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 2,494 once invoked, about $0.0002 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.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.