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.
npx skills add oborchers/fractional-cto --skill research-methodologygit clone --depth 1 https://github.com/oborchers/fractional-ctoWrote 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.
[](https://agentmods.dev/skills/oborchers/fractional-cto/research-methodology)<a href="https://agentmods.dev/skills/oborchers/fractional-cto/research-methodology"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/research-methodology/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.
<a href="https://agentmods.dev/skills/oborchers/fractional-cto/research-methodology"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/research-methodology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00091 | $0.01262 |
| Opus 5 | $0.00046 | $0.00631 |
| Sonnet 5 | $0.00018 | $0.00252 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
research-methodology 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Methodology
Effective research requires deliberate planning before execution. Without decomposition, complex queries overwhelm LLMs — the compositionality gap means models answer sub-questions correctly but fail to compose them into correct multi-hop answers, and this gap does not shrink with model scale alone (Press et al., EMNLP 2023).
Query Analysis
Before decomposing, analyze the query along three dimensions:
Complexity classification:
| Level | Characteristics | Example | Approach |
|---|---|---|---|
| Simple | Single fact, one source sufficient | "What is the GAIA benchmark?" | Direct search, no decomposition |
| Moderate | 2-4 facets, comparison or analysis | "How does LangGraph compare to CrewAI?" | 2-4 parallel subtopics |
| Complex | Multi-faceted, requires synthesis across domains | "How should we architect a deep research agent?" | Full decomposition with dynamic replanning |
Scope narrowing: If a query is vague or overly broad, ask 2-3 clarifying questions before researching. Model this on Claude's desktop deep research flow — refine scope before committing resources.
Questions to consider:
- What specific aspect matters most?
- What is the intended use of this research?
- Are there known constraints (domain, time period, technology)?
Decomposition Strategies
Decomposition strategy should emerge from the query, not from a preset template. The number of subtopics is a function of query complexity, not a fixed constant.
Self-Ask pattern — For multi-hop factual queries. Ask explicit follow-up sub-questions, answer each independently, then compose. Each sub-question becomes a natural insertion point for web search (Press et al., 2023).
Parallel decomposition — For queries with independent facets. Identify subtopics that can be researched simultaneously without dependency. ParallelSearch research shows 12.7% improvement on parallelizable questions using only 69.6% of LLM calls versus sequential approaches (Zhao et al., 2025).
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.
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.
- 12d ago First seen · 100 lines · 91 tokens per session scan A 8ae77cbc397d
research-methodology is a skill published in the GitHub repository oborchers/fractional-cto (30 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 1,262 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
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…
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…