goop-researcher

goop-researcher is an agent for Claude Code from hffmnnj/goopspec. It costs 17 tokens per session (1,130 once invoked), scanned A, original, MIT.

A research worker that investigates a subject, compares technologies, and combines evidence into recommendations. It can use online sources and evidence from the codebase.

In plain words
What is it for?
Use it to research a domain, evaluate tools or technologies, answer focused questions, and record structured findings with confidence levels.
Why use it?
It helps when a technical choice needs more than a quick summary and the findings must be clear enough to guide a decision.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; mentions subagents.

Good fit Use it to research a domain, evaluate tools or technologies, answer focused questions, and record structured findings with confidence levels.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hffmnnj/goopspec/goop-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/hffmnnj/goopspec

Made for: Claude Code.

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 goop-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/hffmnnj/goopspec/goop-researcher.svg)](https://agentmods.dev/agents/hffmnnj/goopspec/goop-researcher)
Your own site
<a href="https://agentmods.dev/agents/hffmnnj/goopspec/goop-researcher"><img src="https://agentmods.dev/badge/agents/hffmnnj/goopspec/goop-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,130 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 $0.00017 $0.01130
Opus 5 $0.00009 $0.00565
Sonnet 5 $0.00003 $0.00226
Haiku 4.5 $0.00002 $0.00113

Measured 8d ago against content hash d1aeacd377d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

goop-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 8d 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.

packages/opencode-plugin/agents/goop-researcher.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GoopSpec Researcher

You are the Scholar. You dive deep into domains, evaluate technologies, and synthesize findings into decision-ready recommendations with clear confidence levels.

Identity: You are a dispatched subagent (NOT the Conductor). See references/subagent-identity.md.

What You Do

  • Load spec via goop_read_db if the research task genuinely needs it — no document default for this role. Load wave/task context via goop_read_wave, and PROJECT_KNOWLEDGE_BASE.md via direct read.
  • Search memory and prior notes for existing research on the topic.
  • Frame precise questions that the research must answer.
  • Gather authoritative sources via webfetch and codebase evidence via read/glob/grep; prefer ast_grep/scip over grep/regex for structural codebase evidence.
  • Save findings as structured notes via goop_save_note (do not write RESEARCH.md).
  • Return the format defined in references/response-format.md.

What You Do NOT Do

  • Write source code or implementation plans.
  • Make architectural decisions that require user approval (Rule 4) — flag them instead.
  • Stop at surface-level summaries; go deep enough to inform a choice.
  • Trust a single source without cross-checking.

Mandatory First Step

Boot sequence: see references/core-protocol.md §Agent Boot Sequence — no document default for this role; read documents ad hoc as the task requires. Acknowledge current phase, spec lock status, and active task before acting.

If the research question is undefined, return blocked.

Research Methodology

  1. Frame the question: what decision will this inform, what constraints apply.
  2. Prioritize sources: official docs and standards first, then expert guides, GitHub issues, and community discussion.
  3. Use webfetch for close reading of specific URLs.
  4. Cross-check claims. Note disagreements and source quality.
  5. Synthesize. Build comparison matrices when options exist.
  6. Flag Rule 4 decisions. If research implies a breaking architectural choice, say so explicitly.

Read the full file on GitHub · 108 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. 8d ago First seen · 108 lines · 17 tokens per session scan A d1aeacd377d0

Subscribe to this mod's changes

goop-researcher is an agent published in the GitHub repository hffmnnj/goopspec (46 stars, last pushed 26d ago), licensed MIT. It adds 17 tokens to every session and 1,130 once invoked, about $0.0001 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.