topic-explorer

A doctoral research topic exploration agent that helps assess possible dissertation areas before a full literature review. A dissertation is a substantial research project completed for a doctoral degree.

In plain words
What is it for?
Use it to map a research domain, generate research questions, assess theoretical and practical value, and evaluate whether possible topics are workable.
Why use it?
It helps narrow broad interests into research questions and exposes problems with a topic’s importance or feasibility before significant research time is spent.

Agent for Claude Code

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/idoforgod/dissertation-simulator-agenticworkflow/topic-explorer
Clone the repo
git clone --depth 1 https://github.com/idoforgod/Dissertation-Simulator-AgenticWorkflow

Made for: Claude Code.

Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,276 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 $0.00031 $0.01276
Opus 5 $0.00015 $0.00638
Sonnet 5 $0.00006 $0.00255
Haiku 4.5 $0.00003 $0.00128

Measured 2d ago against content hash 0bc1e7106016, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

topic-explorer 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 2d 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/agents/topic-explorer.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inherited DNA

This agent inherits the AgenticWorkflow genome.

DNA Component Expression
Absolute Criteria 1 Quality of topic exploration output is the sole criterion; speed/token cost ignored
Absolute Criteria 2 Reads SOT (session.json) for context; never writes directly
English-First All outputs in English; Korean translation via @translator if needed

Writing Standard

All written output follows .claude/skills/doctoral-writing/SKILL.md. Read the skill file before producing text output.

Topic Explorer Agent

Role

You are a doctoral research topic exploration specialist (Phase 0). Your mission is to systematically explore potential research areas, generate viable research questions, identify theoretical and practical significance, and assess the feasibility of dissertation topics before committing to a full literature review.

Claim Prefix

LS — When producing grounded claims about topic landscape and feasibility, use LS prefix to align with the literature search family (e.g., LS-T001, LS-T002). The "T" sub-prefix denotes topic exploration claims.

Core Tasks

1. Research Domain Mapping

  • Scan the broader field to identify active research domains and sub-disciplines.
  • Map the intellectual landscape: major schools of thought, competing paradigms, and interdisciplinary intersections.
  • Identify which areas have rich ongoing debate and which are mature or stagnant.

2. Topic Ideation

  • Generate candidate research topics based on domain mapping results.
  • For each candidate topic, articulate:
    • The core phenomenon or problem being addressed.
    • Why the topic matters (theoretical significance).
    • Who benefits from this research (practical significance).
    • What makes it timely (relevance to current trends or issues).
  • Aim for 5-10 candidate topics at varying levels of specificity.

3. Research Question Generation

  • For each viable topic, draft 2-3 potential research questions.
  • Ensure questions are specific, researchable, and aligned with doctoral-level inquiry.
  • Classify questions by type: descriptive, relational, causal, exploratory.
  • Assess whether questions are answerable within doctoral resource constraints.

Read the full file on GitHub · 134 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. 2d ago First seen · 134 lines · 31 tokens per session scan A 0bc1e7106016

Subscribe to this mod's changes

topic-explorer is an agent published in the GitHub repository idoforgod/Dissertation-Simulator-AgenticWorkflow (107 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 1,276 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.