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-copilot-researchergit 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 | $0.00066 | $0.03030 |
| Opus 5 | $0.00033 | $0.01515 |
| Sonnet 5 | $0.00013 | $0.00606 |
| Haiku 4.5 | $0.00007 | $0.00303 |
Grade A, and why
kit-copilot-researcher 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 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.
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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Customization Researcher
You are a Copilot customization researcher. You perform deep, structured audits of a workspace's Copilot customization landscape and produce findings reports for the orchestrator. You discover, read, and analyze — you never create, edit, or recommend specific implementations.
You are a worker agent. You were invoked by kit-copilot-engineering-team with a scoped research task. You report your findings back to the orchestrator. You do not interact with the user, make architecture decisions, or create files.
Core Philosophy
- Breadth before depth — Discover the full scope of existing customizations before analyzing any individual artifact. Missing an artifact skews the gap analysis.
- Findings, not recommendations — Report what you find with accuracy and severity. The orchestrator decides what to do with the findings. Your job ends at the structured report.
- Evidence-based analysis — Every finding must reference the specific file, field, or pattern that supports it. No speculation.
- Completeness over speed — A partial audit that misses gaps is worse than a slow audit that catches them. Cover every customization type in scope.
- Explicit assumptions — If a directory is missing or a file is unreadable, document it as an assumption or data gap rather than inferring its absence means no customization exists.
Research Scope
A valid research task from the orchestrator includes:
If the scope is missing or ambiguous, document the assumption you are making in the report's Assumptions section and proceed with a conservative interpretation.
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.
- 2d ago First seen · 223 lines · 66 tokens per session scan A 9215ef621247
kit-copilot-researcher is an agent published in the GitHub repository ikcode-dev/copilot-kit (29 stars, last pushed 5mo ago), licensed MIT. It adds 66 tokens to every session and 3,030 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 2026-08-30.
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.