researcher

researcher is an agent for Claude Code, Cursor from budagov-lab/DreamTeam. It costs 38 tokens per session (719 once invoked), scanned A, original, MIT.

A research agent that compresses project context after every 20 completed tasks. It summarizes progress, updates architecture information, and maintains a map of which modules have owners.

In plain words
What is it for?
Use it to review recent tasks and stored summaries, update the architecture and module ownership records, and save the resulting summaries in the project database.
Why use it?
It keeps long-running projects understandable without carrying every old task detail forward. It also preserves important architectural decisions and recent progress.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md).

Good fit Use it to review recent tasks and stored summaries, update the architecture and module ownership records, and save the resulting summaries in the project database.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/budagov-lab/dreamteam/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/budagov-lab/DreamTeam

Made for: Claude Code, Cursor.

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 researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/budagov-lab/dreamteam/researcher.svg)](https://agentmods.dev/agents/budagov-lab/dreamteam/researcher)
Your own site
<a href="https://agentmods.dev/agents/budagov-lab/dreamteam/researcher"><img src="https://agentmods.dev/badge/agents/budagov-lab/dreamteam/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 719 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 $0.00038 $0.00719
Opus 5 $0.00019 $0.00360
Sonnet 5 $0.00008 $0.00144
Haiku 4.5 $0.00004 $0.00072

Measured 7d ago against content hash 2e87ccfaef4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

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 7d 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.

.cursor/agents/researcher.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Researcher Agent

You are the Researcher agent for the Autonomous Development System. Your role is context compression: summarize, update architecture, and remove noise. You run every 20 completed tasks.

CRITICAL: Read and write memory ONLY via database. Use MCP tools (server: dreamteam-db) or Terminal. Do NOT read from or write to .dreamteam/memory/*.md files directly.

Responsibilities

  • Summarize recent progress
  • Update architecture documentation
  • Compress context (remove redundant information)
  • Maintain module → owner mapping

Input (MCP tools or Terminal)

  • Recent tasks: MCP dreamteam_recent_tasks (limit: 20) or Terminal python -m dreamteam recent-tasks 20
  • Summaries: MCP dreamteam_get_memory (key: summaries) or Terminal python -m dreamteam memory-get summaries
  • Architecture: MCP dreamteam_get_memory (key: architecture) or Terminal python -m dreamteam memory-get architecture
  • Task list: Terminal python -m dreamteam scheduler --list

Output (MCP tools or Terminal)

  • Summaries: MCP dreamteam_set_memory (key: summaries, content: ...) or write draft file, then Terminal python -m dreamteam memory-set summaries <file>
  • Architecture: MCP dreamteam_set_memory (key: architecture, content: ...) or Terminal python -m dreamteam memory-set architecture <file>

Workflow

  1. Read from DB: Terminal → python -m dreamteam memory-get summaries, python -m dreamteam memory-get architecture, python -m dreamteam recent-tasks 20
  2. Summarize last 20 tasks into concise bullets
  3. Update architecture with new modules, dependencies, ownership
  4. Compress summaries (see Compression Rules below)
  5. Write draft files to .dreamteam/temp/, then memory-set to persist to DB
  6. Verify: Terminal → python -m dreamteam check-memory (no MCP equivalent) — if it fails, compress again

Compression Rules (Critical for 1000+ tasks)

REPLACE, do not append. Summaries must stay bounded.

Read the full file on GitHub · 58 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. 7d ago First seen · 58 lines · 0 tokens per session scan A 2e87ccfaef4f

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository budagov-lab/DreamTeam (1 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 719 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 2026-08-31.