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 using-deep-researchgit 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/using-deep-research)<a href="https://agentmods.dev/skills/oborchers/fractional-cto/using-deep-research"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/using-deep-research/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/using-deep-research"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/using-deep-research.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 | $0.00070 | $0.00745 |
| Opus 5 | $0.00035 | $0.00373 |
| Sonnet 5 | $0.00014 | $0.00149 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
using-deep-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 10d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research Methodology
Structured deep research transforms ad-hoc web searches into a repeatable, hallucination-resistant research pipeline. Without deliberate structure, research agents gravitate toward the first sources found, fail to verify claims, and produce confident reports built on unreliable foundations.
This plugin provides 4 methodology skills and the /deep-research:research command for orchestrated multi-agent research sessions.
How to Access Skills
Use the Skill tool to invoke any skill by name. When invoked, follow the skill's guidance directly.
Principle Skills
| Skill | Triggers On |
|---|---|
deep-research:research-methodology |
Starting any research task — query analysis, decomposition strategies, effort scaling, dynamic replanning, stopping criteria |
deep-research:source-evaluation |
Evaluating sources — credibility ranking (T1-T6 tiers), multi-provider search strategy, SEO spam detection, domain-specific source selection |
deep-research:hallucination-prevention |
Any research output — hallucination taxonomy, citation verification rules, circuit breaker patterns, confidence scoring, cascading prevention |
deep-research:synthesis-and-reporting |
Combining findings — deduplication, conflict resolution, narrative construction, citation formatting, report quality assessment |
When to Invoke Skills
Invoke a skill when there is even a small chance the work touches one of these areas:
- Starting research: Load
research-methodologyto plan decomposition and effort scaling - Searching the web: Load
source-evaluationto assess what you find - Writing any claim: Load
hallucination-preventionto verify before stating - Combining findings: Load
synthesis-and-reportingto merge and cite properly
The /deep-research:research Command
For full orchestrated research sessions, use /deep-research:research. The command:
- Checks web access permissions (one-time setup per project)
- Analyzes the research query — if too vague, asks 2-3 clarifying questions
- Decomposes into subtopics based on query complexity (not a fixed number)
- Spawns parallel
research-workeragents (Sonnet) — each writes findings with a Verifiable Claims Table - Spawns parallel
research-verifieragents (Sonnet) — each re-fetches sources and checks claims independently - Dispatches a
research-synthesizeragent (Opus) — applies corrections, merges findings, writes final document with Confidence Assessment - Preserves intermediate docs and verification reports for traceability
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.
- 10d ago First seen · 55 lines · 70 tokens per session scan A c3a626f90ae1
using-deep-research is a skill published in the GitHub repository oborchers/fractional-cto (29 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 745 once invoked, about $0.0003 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…