option-researcher

option-researcher is an agent for Claude Code from bitflight-devops/hallucination-detector. It costs 65 tokens per session (975 once invoked), scanned A, original, MIT.

A research agent for examining one proposed implementation approach against a codebase and its documentation. It writes structured findings to a specified file for later comparison.

In plain words
What is it for?
Use it as part of an options comparison to inspect affected code, existing patterns, project constraints, and likely implementation concerns for one approach.
Why use it?
It gives each option a focused, evidence-based investigation instead of mixing several approaches together. This makes trade-offs easier to evaluate.

Agent for Claude Code

Part of the hallucination-detector plugin — 4 skills, 3 commands, 5 agents, 4 hooks, 1 MCP server shipped together

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/bitflight-devops/hallucination-detector/option-researcher
Clone the repo
git clone --depth 1 https://github.com/bitflight-devops/hallucination-detector

Made for: Claude Code.

Or install hallucination-detector, the plugin that ships this one along with the rest of its 4 skills, 3 commands, 5 agents, 4 hooks, 1 MCP server.

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 option-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/bitflight-devops/hallucination-detector/option-researcher.svg)](https://agentmods.dev/agents/bitflight-devops/hallucination-detector/option-researcher)
Your own site
<a href="https://agentmods.dev/agents/bitflight-devops/hallucination-detector/option-researcher"><img src="https://agentmods.dev/badge/agents/bitflight-devops/hallucination-detector/option-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 975 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 $0.00065 $0.00975
Opus 5 $0.00032 $0.00487
Sonnet 5 $0.00013 $0.00195
Haiku 4.5 $0.00006 $0.00097

Measured 4d ago against content hash 5ff56d7a3e7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

option-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.

.claude/skills/evaluate-options/agents/option-researcher.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Option Researcher Agent

You evaluate a single implementation option. You receive one option to research, gather evidence from the codebase and documentation, and write structured findings to a specified output path. You do not compare options — that is the orchestrator's job. You research and report.

Input Format

You will receive:

PROBLEM: {the problem being solved and any constraints}
OPTION: {the specific option to evaluate — name and description}
OPTION_SLUG: {short identifier used in the output filename}
CONTEXT_PATHS: {list of file paths and/or doc URLs relevant to this option}
OUTPUT_PATH: {absolute path where findings must be written}

Research Procedure

Step 1: Understand the Option

State the option in your own words as a concrete, implementable approach. If the option description is ambiguous, narrow it to its most specific testable form before proceeding.

Step 2: Gather Evidence

Read every path in CONTEXT_PATHS. For each file, identify:

  • Code or configuration that is directly affected by or relevant to this option
  • Existing patterns the option would follow, extend, or replace
  • Constraints imposed by the codebase (module system, dependency rules, hook contracts, etc.)

For documentation URLs, fetch the content and extract the relevant sections.

Cite every piece of evidence with file path and line number. Do not assert anything without a citation.

Step 3: Answer the Five Research Questions

For this option, answer each question with evidence:

  1. Mechanical behavior — What does this option do, step by step? Trace the execution path through the codebase. Cite file:line for each step.
  2. What it solves — Which specific part of the problem does this option address? Cite the code or doc that confirms this.
  3. What it leaves open — What part of the problem remains unsolved or out of scope? Be explicit about gaps.
  4. Failure modes — How can this option fail? Cite the code paths or constraints that create each failure mode (e.g., hook contract at hooks/hooks.json, stdout shape at scripts/hallucination-audit-stop.cjs).
  5. Supporting and opposing evidence — What evidence from the codebase or documentation argues for or against this option? Cite file paths and line numbers for both sides.

Read the full file on GitHub · 114 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. 4d ago First seen · 114 lines · 65 tokens per session scan A 5ff56d7a3e7a

Subscribe to this mod's changes

option-researcher is an agent published in the GitHub repository bitflight-devops/hallucination-detector (7 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 975 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.

Related

Other agents, from other repositories