research

research is a skill for Claude Code, Codex from wsauret/flywheel. It costs 43 tokens per session (1,096 once invoked), scanned A, original, MIT.

A codebase research workflow that maps how an existing software system is organized and connected, then saves the findings in a persistent document.

In plain words
What is it for?
Use it to investigate a codebase, trace relevant files and references, and document the current implementation.
Why use it?
It helps you understand what the code already does before planning changes, without mixing in recommendations or redesign ideas.

Skill for Claude CodeCodex

Part of the flywheel plugin — 15 skills, 15 agents 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 skills/wsauret/flywheel/research
Any agent
npx skills add wsauret/flywheel --skill research
Clone the repo
git clone --depth 1 https://github.com/wsauret/flywheel

Made for: Claude Code, Codex.

Or install flywheel, the plugin that ships this one along with the rest of its 15 skills, 15 agents.

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 research

README.md
[![agentmods](https://agentmods.dev/badge/skills/wsauret/flywheel/research.svg)](https://agentmods.dev/skills/wsauret/flywheel/research)
Your own site
<a href="https://agentmods.dev/skills/wsauret/flywheel/research"><img src="https://agentmods.dev/badge/skills/wsauret/flywheel/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,096 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 $0.00043 $0.01096
Opus 5 $0.00022 $0.00548
Sonnet 5 $0.00009 $0.00219
Haiku 4.5 $0.00004 $0.00110

Measured 4d ago against content hash bccd088acefe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research 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.

flywheel/skills/research/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Research Skill

Conduct comprehensive research using a two-phase locate-then-analyze approach that reduces context usage by 40-60%.

Philosophy: Documentarian Mode

  • Document what IS, not what SHOULD BE
  • No suggestions, critiques, or recommendations
  • Pure technical mapping of the existing system
  • Focus on paths and references, not full file contents

Input

Research question via $ARGUMENTS. If empty, ask user.


Phase 0: Check for Existing Research

Before starting new research, check if recent research already covers this topic:

find docs/research -name "*<topic-slug>*" -mtime -14 2>/dev/null | head -3

If matches found, read the YAML frontmatter (topic, tags) to assess relevance. If a strong match exists:

AskUserQuestion: "Found recent research: [filename] ([N] days old). Reuse, refresh, or start new?"

  • Reuse (Recommended) — Read existing doc, skip to Phase 3 (summary)
  • Refresh — Use existing doc as starting point, re-run locate/analyze to update
  • Start new — Proceed normally

If no matches or no docs/research/ directory, proceed to Phase 1.


Phase 1: Research Workflow

Run the canonical research workflow: all four locators in parallel → consolidate → all four analyzers in parallel.

Read flywheel/skills/flywheel-conventions/references/research-workflow.md before proceeding — it contains locator templates, the consolidation rule (top-N selection per analyzer), and analyzer templates.


Phase 2: Synthesize & Persist

Map the canonical analyzer outputs to research-doc sections:

  • analyzer-codebase findings → "Codebase Map" (file structure, components, interactions; file:line refs).
  • analyzer-patterns findings → "Patterns" (named patterns with code examples and locations).
  • analyzer-docs findings → "Decisions & Constraints" (extracted ADR / doc content).
  • analyzer-web findings → "External References" (URL citations with extracted content).

The canonical analyzers' flags fold into a "Concerns & Open Questions" section:

Read the full file on GitHub · 132 lines

Files

What ships with it

1 file 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.

  1. 4d ago First seen · 132 lines · 43 tokens per session scan A bccd088acefe

Subscribe to this mod's changes

research is a skill published in the GitHub repository wsauret/flywheel (14 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,096 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.