deepresearch-v2

deepresearch-v2 is a skill for Claude Code, Codex from jakkaj/tools. It costs 29 tokens per session (579 once invoked), scanned A, original, MIT.

A skill that prepares structured research prompts for agents investigating coding problems.

In plain words
What is it for?
It is for framing coding research questions, including technology details, domain boundaries, related contracts, and the ownership and impact of a proposed fix.
Why use it?
It helps an investigating agent receive the problem, technical context, error details, and affected software areas in a consistent format.

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/jakkaj/tools/deepresearch-v2
Any agent
npx skills add jakkaj/tools --skill deepresearch-v2
Clone the repo
git clone --depth 1 https://github.com/jakkaj/tools

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.

agentmods badge for deepresearch-v2

README.md
[![agentmods](https://agentmods.dev/badge/skills/jakkaj/tools/deepresearch-v2.svg)](https://agentmods.dev/skills/jakkaj/tools/deepresearch-v2)
Your own site
<a href="https://agentmods.dev/skills/jakkaj/tools/deepresearch-v2"><img src="https://agentmods.dev/badge/skills/jakkaj/tools/deepresearch-v2.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 579 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 $0.00029 $0.00579
Opus 5 $0.00015 $0.00290
Sonnet 5 $0.00006 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 5d ago against content hash e2506e8116e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deepresearch-v2 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 5d 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/SDD/deepresearch-v2/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Please deep think / ultrathink as this is a complex task.

deepresearch-v2

Craft a structured research prompt to leverage a deep research agent for solving coding challenges. Domain-aware: surfaces boundary concerns and cross-domain impacts when relevant.


Pre-flight: Load Domain Context

Before crafting the prompt, check for domain context:

  • If docs/domains/registry.md exists → scan registered domains
  • If docs/domains/domain-map.md exists → note domain relationships and contract edges
  • For domains related to the problem → read docs/domains/<slug>/domain.md (concepts, contracts, composition)

If no domain system is present, skip this step and proceed normally.


Crafting the Research Prompt

Please create a structured prompt with the following sections:

1. Clear Problem Definition

  • Precisely define the issue we are facing.
  • Include relevant error messages, stack traces, or problematic behaviors.
  • Which domain(s) does this problem affect? Does it cross domain boundaries?
  • If multi-domain: which domain owns the fix vs. which domains are impacted?

2. Contextual Information

  • Specify the technology stack involved (languages, frameworks, libraries).
  • Include exact versions of key dependencies and any recent updates.
  • Mention any recent codebase changes potentially related to the problem.
  • Note domain-specific dependencies: contracts consumed, contracts exposed, shared infrastructure.
  • Flag domain separation concerns — is the problem caused by tight coupling across boundaries?

3. Key Research Questions

  • Identify clear, actionable research questions to guide the deep research agent.
  • Ensure these questions target resolving our current challenge directly.
  • If domains are involved: Does the solution respect existing domain boundaries? Should a contract be introduced or modified?

4. Recommended Tools and Resources

  • List specific tools, libraries, or methodologies we should investigate.
  • Include any helpful links or references.

Read the full file on GitHub · 70 lines

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. 5d ago First seen · 70 lines · 29 tokens per session scan A e2506e8116e6

Subscribe to this mod's changes

deepresearch-v2 is a skill published in the GitHub repository jakkaj/tools (5 stars, last pushed 19d ago), licensed MIT. It adds 29 tokens to every session and 579 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

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