What is research[A]-exploration?

A research workflow stage for exploring a vague research interest until it becomes a grounded direction with clear research questions. It produces the first part of an idea report and leads to the next research stage.

Use it to explore possible directions, converge on research questions, and record the result in docs/idea_report.md.

An initial topic is often too broad to guide focused research or experiments.

research[A]-exploration — Skill for Claude Code and Codex by LMDHQ-042

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.

Any agent

npx skills add LMDHQ-0420/ResearchPilot-Skills --skill research-a-exploration

Clone the repo

git clone --depth 1 https://github.com/LMDHQ-0420/ResearchPilot-Skills

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lmdhq-0420/researchpilot-skills/research-a-exploration/github.svg)](https://agentmods.dev/skills/lmdhq-0420/researchpilot-skills/research-a-exploration)

Your own site

<a href="https://agentmods.dev/skills/lmdhq-0420/researchpilot-skills/research-a-exploration"><img src="https://agentmods.dev/badge/skills/lmdhq-0420/researchpilot-skills/research-a-exploration/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lmdhq-0420/researchpilot-skills/research-a-exploration"><img src="https://agentmods.dev/badge/skills/lmdhq-0420/researchpilot-skills/research-a-exploration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,524 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00017	$0.01524
Opus 5	$0.00009	$0.00762
Sonnet 5	$0.00003	$0.00305
Haiku 4.5	$0.00002	$0.00152

Measured 13d ago against content hash 7d03140e632f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

research[A]-exploration 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 13d 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.

skills/ResearchPilot-Skills-en/research[A]-exploration/SKILL.md · 174 lines

How it starts

The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.

user_requirements.md priority: All user constraints recorded in docs/user_requirements.md (direction preferences, implementation requirements, document format, etc.) take precedence over any default instruction in this skill. Always read that file before generating any output to ensure compliance with confirmed user constraints.

Phase A: Direction Exploration

Starting from a vague research interest, converge through multi-turn interaction to a well-grounded research direction and a clear set of research questions (RQs). Produces docs/idea_report.md Part 1, then moves to Phase B.

Workflow Overview & Outputs

ResearchPilot-Skills splits a complete academic research project into seven independent stage skills. The current skill is one link in that chain.

Seven-Stage Chain

Skill	Phase	Main Output
`/research[A]-exploration`	Direction Exploration	`docs/idea_report.md` Part 1
`/research[B]-idea`	Idea Deepening	`docs/idea_report.md` Part 2
`/research[C]-experiment`	Experiment Design	`docs/idea_report.md` Part 3
`/research[D]-implementation`	Implementation Design	`docs/implementation.md`
`/research[E]-coding`	Coding	`code/` + `docs/dev_log.md`
`/research[F]-iteration`	Code Iteration	`dev_log.md` iteration records
`/research[G.0]-plan`	Paper Planning	manuscript architecture + `notebooks/figures.ipynb`
`/research[G.1]-method`	Method	manuscript Method section
`/research[G.2]-experiments`	Experiments	manuscript Experiments section
`/research[G.3]-abstract`	Abstract	manuscript Abstract
`/research[G.4]-introduction`	Introduction	manuscript Introduction
`/research[G.5]-related`	Related Works	manuscript Related Works
`/research[G.6]-conclusion`	Conclusion + References	manuscript Conclusion
`/research[G.7]-review`	Full-paper Review	review report

Project Directory Structure

docs/
  idea_report.md        # Research report in three parts:
                        #   Part 1: Motivation, RQs, Key Works  (Phase A)
                        #   Part 2: Introduction, Related Works, Method  (Phase B)
                        #   Part 3: Datasets, Experiment Design, Resource Estimate  (Phase C)
  implementation.md     # Coding guide: file- and function-level implementation plan  (Phase D)
  dev_log.md            # Dev log: progress, decisions, "How to Run" section  (Phase E)
  user_requirements.md  # User constraints: collected and maintained by Claude
  papers/               # Downloaded paper PDFs or abstract TXTs
  manuscripts/          # Paper drafts, each revision archived separately
                        #   (e.g. v1.0-initial-draft.md, v1.1-revision.md)

code/
  src/                  # Core model and training code
  scripts/              # Run scripts (train.sh, evaluate.sh, ablation.sh)
  configs/              # Hyperparameter config files
  src/models/baseline/  # Baseline implementations (interface matches main model)
  notebooks/            # Visualization notebooks; paper figure/table generation
  data/                 # Datasets (gitignored)
  results/              # Experiment results (gitignored)
  logs/                 # Training logs (gitignored)
  README.md             # Environment setup and run commands
  requirements.txt      # Dependencies (library names only, no torch family)

Read the full file on GitHub · 174 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

13d ago First seen · 174 lines · 17 tokens per session scan A 7d03140e632f

Subscribe to this mod's changes

research[A]-exploration is a skill published in the GitHub repository LMDHQ-0420/ResearchPilot-Skills (284 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 1,524 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.

Research

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens