research

A research workflow that combines web searches, local codebase exploration, and written synthesis into a structured report.

In plain words
What is it for?
Use it to investigate a topic, inspect related code and configuration, compare web findings with the codebase, and produce a report with sources and actionable recommendations.
Why use it?
It brings outside information and relevant project files together so findings, gaps, confidence levels, and recommendations can be reviewed in one place.

Skill for Claude CodeCodex

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/billbuchanan-code/claude-code-power-setup/research
Any agent
npx skills add billbuchanan-code/claude-code-power-setup --skill research
Clone the repo
git clone --depth 1 https://github.com/billbuchanan-code/claude-code-power-setup

Made for: Claude Code, Codex.

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 343 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 $0.00016 $0.00343
Opus 5 $0.00008 $0.00171
Sonnet 5 $0.00003 $0.00069
Haiku 4.5 $0.00002 $0.00034

Measured yesterday against content hash 765e8b8fc7cb, 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 yesterday.

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/research/SKILL.md · 47 lines

What it actually says

Deep Research Skill

Perform deep research on a given topic by combining web search, codebase exploration, and synthesis into a comprehensive report.

Process

  1. Parse the research question from $ARGUMENTS
  2. Search the web for current information using WebSearch. Run multiple queries with different phrasings to get broad coverage. Use WebFetch to read the most relevant results in detail.
  3. Explore the local codebase for relevant context using Grep, Glob, and Read. Look for related code, configuration, documentation, and dependencies.
  4. Synthesize findings into a structured research report that connects web findings with codebase context.
  5. Include sources, confidence levels, and actionable recommendations for each finding.

Output Format

Structure the output as a Research Report with the following sections:

Executive Summary

A 2-3 sentence overview of the key findings.

Web Findings

Bullet points of what was discovered from web searches, with source URLs.

Codebase Findings

Relevant code, configuration, or documentation found in the local project, with file paths.

Synthesis

How the web findings and codebase findings connect. Identify gaps, risks, or opportunities.

Sources

A numbered list of all sources consulted (URLs, file paths).

Recommended Next Steps

Actionable items ranked by priority, with confidence level (High / Medium / Low) for each recommendation.

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. yesterday First seen · 47 lines · 16 tokens per session scan A 765e8b8fc7cb

Subscribe to this mod's changes

research is a skill published in the GitHub repository billbuchanan-code/claude-code-power-setup (2 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 343 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

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

obra/superpowers · 21 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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens