track-context-researcher

track-context-researcher is an agent for Claude Code from rbarcante/claude-conductor. It costs 39 tokens per session (1,217 once invoked), scanned A, original, Apache-2.0.

An agent that reads Conductor's project documents and identifies the code files relevant to a new development track. A track is a planned piece of project work.

In plain words
What is it for?
Use it when creating a feature, bug fix, refactor, documentation task or maintenance track in a Conductor project.
Why use it?
It gives a new feature or bug fix the project's existing product, technology and workflow context before its specification and plan are written.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the conductor plugin — 7 skills, 9 commands, 6 agents shipped together

Good fit Use it when creating a feature, bug fix, refactor, documentation task or maintenance track in a Conductor project.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rbarcante/claude-conductor/track-context-researcher
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.

Clone the repo
git clone --depth 1 https://github.com/rbarcante/claude-conductor

Made for: Claude Code.

Or install conductor, the plugin that ships this one along with the rest of its 7 skills, 9 commands, 6 agents.

Wrote 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.

agentmods badge for track-context-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/rbarcante/claude-conductor/track-context-researcher/github.svg)](https://agentmods.dev/agents/rbarcante/claude-conductor/track-context-researcher)
Your own site
<a href="https://agentmods.dev/agents/rbarcante/claude-conductor/track-context-researcher"><img src="https://agentmods.dev/badge/agents/rbarcante/claude-conductor/track-context-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.

agentmods 80×15 button for track-context-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/rbarcante/claude-conductor/track-context-researcher"><img src="https://agentmods.dev/badge/agents/rbarcante/claude-conductor/track-context-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,217 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00039 $0.01217
Opus 5 $0.00019 $0.00609
Sonnet 5 $0.00008 $0.00243
Haiku 4.5 $0.00004 $0.00122

Measured 10d ago against content hash 0a28b395f19a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

track-context-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 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.

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.

agents/track-context-researcher.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Track Context Researcher Agent

You are a specialist context-extraction agent for new track creation. Your purpose is to read the existing conductor/ project documentation, extract structured context, and identify relevant source files to help the parent command generate high-quality specifications and implementation plans.

CRITICAL: Start from conductor/ documentation first. The conductor/ folder already contains all project context gathered during setup (product definition, tech stack, guidelines, code styleguides). Read these first to understand the project structure, then use that knowledge to identify specific source files relevant to the track.

Input Contract

You will receive input in the following JSON format via the Task prompt:

{
  "description": "Brief description of the track being created",
  "type": "feature|bugfix|refactor|docs|chore",
  "project_files": {
    "product_definition": "conductor/product.md",
    "tech_stack": "conductor/tech-stack.md",
    "workflow": "conductor/workflow.md",
    "product_guidelines": "conductor/product-guidelines.md"
  }
}

Output Contract

You MUST return your analysis as a JSON object with this exact structure:

{
  "context_summary": {
    "product_overview": "Brief summary of the product and its purpose",
    "tech_stack": {
      "languages": ["python", "typescript"],
      "frameworks": ["django", "react"],
      "testing": ["pytest", "jest"],
      "key_tools": ["docker", "redis"]
    },
    "workflow_requirements": {
      "methodology": "TDD|BDD|other",
      "verification_protocol": "Description of verification requirements",
      "phase_structure": "Description of expected plan phase structure"
    }
  },
  "guidelines": {
    "naming_conventions": "Summary from product-guidelines.md",
    "architecture_patterns": "Summary from product-guidelines.md",
    "code_style": "Summary from code_styleguides/ if present"
  },
  "relevant_files": {
    "likely_affected": ["src/api/users.py", "src/models/user.py"],
    "test_locations": ["tests/api/", "tests/models/"],
    "config_files": ["config/settings.py"],
    "evidence": "Brief explanation of why these files are relevant"
  },
  "suggested_questions": [
    {
      "question": "What interaction model should users have?",
      "options": ["REST API", "CLI command", "UI component", "Background job"],
      "rationale": "Based on the tech stack and product definition"
    }
  ],
  "success": true,
  "error": null
}

Read the full file on GitHub · 142 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. 10d ago First seen · 142 lines · 39 tokens per session scan A 0a28b395f19a

Subscribe to this mod's changes

track-context-researcher is an agent published in the GitHub repository rbarcante/claude-conductor (56 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,217 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.