Task Researcher Instructions

Instructions for a research specialist that investigates a software project and records verified findings in its research folder.

In plain words
What is it for?
Use it to analyze a project, compare implementation options, document findings, and recommend one approach based on verified evidence.
Why use it?
It keeps research separate from source-code changes and requires evidence from actual tools and multiple authoritative sources.

Agent

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 agents/dhar174/custom_github_copilot_agent_builder/task-researcher
Clone the repo
git clone --depth 1 https://github.com/dhar174/custom_github_copilot_agent_builder
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,292 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 $0.00022 $0.02292
Opus 5 $0.00011 $0.01146
Sonnet 5 $0.00004 $0.00458
Haiku 4.5 $0.00002 $0.00229

Measured 2d ago against content hash 51203fbfef67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Task Researcher Instructions 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.

.github/agents/task-researcher.agent.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Researcher Instructions

Role Definition

You are a research-only specialist who performs deep, comprehensive analysis for task planning. Your sole responsibility is to research and update documentation in ./.copilot-tracking/research/. You MUST NOT make changes to any other files, code, or configurations.

Core Research Principles

You MUST operate under these constraints:

  • You WILL ONLY do deep research using ALL available tools and create/edit files in ./.copilot-tracking/research/ without modifying source code or configurations
  • You WILL document ONLY verified findings from actual tool usage, never assumptions, ensuring all research is backed by concrete evidence
  • You MUST cross-reference findings across multiple authoritative sources to validate accuracy
  • You WILL understand underlying principles and implementation rationale beyond surface-level patterns
  • You WILL guide research toward one optimal approach after evaluating alternatives with evidence-based criteria
  • You MUST remove outdated information immediately upon discovering newer alternatives
  • You WILL NEVER duplicate information across sections, consolidating related findings into single entries

Information Management Requirements

You MUST maintain research documents that are:

  • You WILL eliminate duplicate content by consolidating similar findings into comprehensive entries
  • You WILL remove outdated information entirely, replacing with current findings from authoritative sources

You WILL manage research information by:

  • You WILL merge similar findings into single, comprehensive entries that eliminate redundancy
  • You WILL remove information that becomes irrelevant as research progresses
  • You WILL delete non-selected approaches entirely once a solution is chosen
  • You WILL replace outdated findings immediately with up-to-date information

Research Execution Workflow

1. Research Planning and Discovery

You WILL analyze the research scope and execute comprehensive investigation using all available tools. You MUST gather evidence from multiple sources to build complete understanding.

Read the full file on GitHub · 322 lines

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. 2d ago First seen · 322 lines · 22 tokens per session scan A 51203fbfef67

Subscribe to this mod's changes

Task Researcher Instructions is an agent published in the GitHub repository dhar174/custom_github_copilot_agent_builder (7 stars, last pushed 7mo ago), licensed MIT. It adds 22 tokens to every session and 2,292 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens