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/budagov-lab/DreamTeamWrote 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/budagov-lab/dreamteam/researcher)<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>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 | $0.00038 | $0.00719 |
| Opus 5 | $0.00019 | $0.00360 |
| Sonnet 5 | $0.00008 | $0.00144 |
| Haiku 4.5 | $0.00004 | $0.00072 |
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.
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 Terminalpython -m dreamteam recent-tasks 20 - Summaries: MCP
dreamteam_get_memory(key: summaries) or Terminalpython -m dreamteam memory-get summaries - Architecture: MCP
dreamteam_get_memory(key: architecture) or Terminalpython -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 Terminalpython -m dreamteam memory-set summaries <file> - Architecture: MCP
dreamteam_set_memory(key: architecture, content: ...) or Terminalpython -m dreamteam memory-set architecture <file>
Workflow
- Read from DB: Terminal →
python -m dreamteam memory-get summaries,python -m dreamteam memory-get architecture,python -m dreamteam recent-tasks 20 - Summarize last 20 tasks into concise bullets
- Update architecture with new modules, dependencies, ownership
- Compress summaries (see Compression Rules below)
- Write draft files to
.dreamteam/temp/, then memory-set to persist to DB - 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.
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.
- 7d ago First seen · 58 lines · 0 tokens per session scan A 2e87ccfaef4f
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.
Other agents, from other repositories
cut
Over-engineering hunter. Extra files, wrappers, speculative types, npm/bun/yarn, unjustified deps. Use for /cut or "too much code".
prove
Skeptical verifier. Runs the project's real tests and pnpm audit when a JS lockfile exists. Use for /prove or when the work is claimed done.
tailwind-reviewer
Reviews code changes for correct Tailwind CSS v4 usage. Catches v3 patterns, missing accessibility attributes, and inconsistent theming. Use after generating or modifying Tailwind code.
code-review-agent
Autonomous code review agent that analyzes code for security vulnerabilities, quality issues, and best practices adherence.
researcher
Research specialist for domain knowledge, library/tool evaluation, and architecture best practices. Use proactively before implementation when the task involves unfamiliar territory, technology choices, or architectural decisions that benefit from research.
type-generator
Generates types from schemas, APIs, or data structures including OpenAPI, GraphQL, JSON schemas, and API responses. Use for type generation from various sources.