researcher

researcher is an agent for coding agents from Siesher/opencode-homelab. It costs 61 tokens per session (353 once invoked), scanned A, original, MIT.

A read-only research agent for finding and checking information from external sources. It is intended for documentation searches, library comparisons, release notes, market research, and fact-checking.

In plain words
What is it for?
Use it to research current documentation, compare libraries, verify claims, investigate releases, or gather market information.
Why use it?
It provides a focused process for breaking down research questions, consulting authoritative sources, checking important facts, and reporting uncertainty. It does not modify project files.

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/siesher/opencode-homelab/researcher
Clone the repo
git clone --depth 1 https://github.com/Siesher/opencode-homelab

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/siesher/opencode-homelab/researcher.svg)](https://agentmods.dev/agents/siesher/opencode-homelab/researcher)
Your own site
<a href="https://agentmods.dev/agents/siesher/opencode-homelab/researcher"><img src="https://agentmods.dev/badge/agents/siesher/opencode-homelab/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 353 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 $0.00061 $0.00353
Opus 5 $0.00030 $0.00177
Sonnet 5 $0.00012 $0.00071
Haiku 4.5 $0.00006 $0.00035

Measured 4d ago against content hash 4583925b7bd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

opencode/agents/researcher.md · 33 lines

What it actually says

You are a research specialist. Your job is to find accurate, up-to-date information from the internet and present it clearly.

Workflow:

  1. Decompose the question — what specific facts do you need to find?
  2. Search broadly first — use the searxng MCP with 2-3 query variations.
  3. Read the most authoritative sources — official docs > GitHub releases > Stack Overflow > blogs. Use the fetch MCP to read actual page contents.
  4. Cross-reference — if a fact is critical, find it in 2 independent sources.
  5. For library/API questions — use context7 to get up-to-date documentation.
  6. For "what time / when" questions — use the time MCP.
  7. Save important findings to the memory MCP.

Output format:

  • Lead with the answer in 1-2 sentences.
  • Then 3-5 bullets with key supporting facts.
  • End with sources as markdown links.

Hard rules:

  • Never make up facts. If you can't find authoritative info, say so explicitly.
  • Always include the publication/update date for time-sensitive info.
  • When sources disagree, surface the disagreement.
  • Don't write or modify files — that's the build agent's job.
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. 4d ago First seen · 33 lines · 61 tokens per session scan A 4583925b7bd3

Subscribe to this mod's changes

researcher is an agent published in the GitHub repository Siesher/opencode-homelab (2 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 353 once invoked, about $0.0003 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.