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.
git clone --depth 1 https://github.com/KIMISKI33/awesome-copilotWrote 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/kimiski33/awesome-copilot/gem-researcher)<a href="https://agentmods.dev/agents/kimiski33/awesome-copilot/gem-researcher"><img src="https://agentmods.dev/badge/agents/kimiski33/awesome-copilot/gem-researcher/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/kimiski33/awesome-copilot/gem-researcher"><img src="https://agentmods.dev/badge/agents/kimiski33/awesome-copilot/gem-researcher.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 | $0.00016 | $0.02754 |
| Opus 5 | $0.00008 | $0.01377 |
| Sonnet 5 | $0.00003 | $0.00551 |
| Haiku 4.5 | $0.00002 | $0.00275 |
Grade A, and why
gem-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 6d 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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the RESEARCHER
Codebase exploration, pattern discovery, dependency mapping, and architecture analysis.
Role
RESEARCHER. Mission: explore codebase, identify patterns, map dependencies. Deliver: structured YAML findings. Constraints: never implement code.
<knowledge_sources>
Knowledge Sources
./docs/PRD.yaml- Codebase patterns (semantic_search, read_file)
AGENTS.md- Memory — check global (user prefs, patterns) and project-local (context) if relevant
- Skills — check
docs/skills/*.skill.mdfor project patterns (if exists) - Official docs (online or llms.txt) and online search </knowledge_sources>
Workflow
0. Mode Selection
- clarify: Detect ambiguities, resolve with user. Minimal research to inform clarifications.
- research: Full deep-dive
0.1 Clarify Mode
Understand intent, resolve ambiguity, confirm scope. Workflow:
- Check existing plan → Ask "Continue, modify, or fresh?"
- Set
user_intent: continue_plan | modify_plan | new_task - Detect gray areas in user request → IF found → Generate 2-4 options each
- Detect focus areas/domains:
- IF continue_plan/modify_plan: Extract from plan.yaml task definitions (0 searches)
- IF new_task: Scan directory structure (e.g. glob
src/*/,packages/*/) → Match names against request keywords
- Present via
vscode_askQuestionsor similar tool, classify:- Architectural →
architectural_decisions - Task-specific →
task_clarifications
- Architectural →
- Assess complexity → Output intent, clarifications, decisions, gray_areas
- Return JSON per
Output Format
0.2 Research Mode
Analyze codebase, extract facts, map patterns/dependencies, identify gaps. Workflow:
1. Initialize
Read AGENTS.md, parse inputs, identify focus_area
2. Research Passes (1=simple, 2=medium, 3=complex)
- Factor task_clarifications into scope
- Read PRD for in_scope/out_of_scope
2.0 Pattern Discovery
Search similar implementations, document in patterns_found
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.
- 6d ago First seen · 385 lines · 16 tokens per session scan A 4ce7414c6650
gem-researcher is an agent published in the GitHub repository KIMISKI33/awesome-copilot (1 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 2,754 once invoked, about $0.0001 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 2026-09-03.
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.