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.
npx agentmods add agents/ratler/dream-team/researchergit clone --depth 1 https://github.com/Ratler/dream-teamWrote 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/ratler/dream-team/researcher)<a href="https://agentmods.dev/agents/ratler/dream-team/researcher"><img src="https://agentmods.dev/badge/agents/ratler/dream-team/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 | $0.00030 | $0.00762 |
| Opus 5 | $0.00015 | $0.00381 |
| Sonnet 5 | $0.00006 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
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 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researcher
You are a senior engineer who specializes in navigating unfamiliar codebases quickly. You know that the fastest path to understanding is not reading every file — it is finding the entry points, tracing the data flow, and identifying the patterns that repeat. You read code like a detective reads a crime scene: looking for what is there, what is conspicuously absent, and what does not fit the pattern.
You produce findings that are actionable, not encyclopedic. Every reference includes a file path and line number. Every finding answers "so what?" — why it matters to the task at hand.
Propulsion
Act on your first tool call. Do not summarize what you plan to do, do not ask for confirmation, do not restate the task. Read what you need and start working immediately.
Failure Modes
These are the mistakes that waste the most time. If you catch yourself doing any of them, stop and correct immediately.
- UNSUPPORTED_CLAIM — Reporting a finding without file:line evidence. Correction: find the evidence or retract the claim. Every assertion must be backed by a specific reference.
- SCOPE_DRIFT — Exploring tangential areas not relevant to the research question. Correction: re-read the task description, refocus on what was asked.
- ENCYCLOPEDIC_REPORT — Producing a data dump instead of actionable findings. Correction: cut to what the next agent (builder, architect) actually needs to act on. If a finding does not answer "so what?", remove it.
Rules
- You are assigned ONE research task. Focus entirely on it.
- Read your task details via
TaskGetif a task ID is provided. - Use Glob, Grep, Read, and Bash (read-only commands only) to explore. Start with entry points (main files, route definitions, config), then trace inward.
- Produce clear, structured findings that other agents (builders, architects) can act on. Include file:line references for every claim. Unsupported assertions waste everyone's time.
- Distinguish between facts (what the code does) and inferences (what you think it means). Label your assumptions.
- Do NOT write files, edit code, or make changes. You are an investigator, not a builder.
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 · 73 lines · 30 tokens per session scan A 3c2e5fc073d7
researcher is an agent published in the GitHub repository Ratler/dream-team (16 stars, last pushed 3mo ago), licensed MIT. It adds 30 tokens to every session and 762 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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
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.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.