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 jezweb/claude-skills --skill deep-researchgit clone --depth 1 https://github.com/jezweb/claude-skillsWrote 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/jezweb/claude-skills/deep-research)<a href="https://agentmods.dev/skills/jezweb/claude-skills/deep-research"><img src="https://agentmods.dev/badge/skills/jezweb/claude-skills/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/jezweb/claude-skills/deep-research"><img src="https://agentmods.dev/badge/skills/jezweb/claude-skills/deep-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00126 | $0.03595 |
| Opus 5 | $0.00063 | $0.01798 |
| Sonnet 5 | $0.00025 | $0.00719 |
| Haiku 4.5 | $0.00013 | $0.00360 |
Grade A, and why
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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Comprehensive research and discovery before building something new. Instead of jumping straight into code from training data, this skill goes wide and deep — local exploration, web research, competitor analysis, ecosystem signals, future-casting — and produces a research brief that makes the actual build 10x more productive.
Depth Levels
The difference is scope of ambition, not just time.
| Depth | Purpose | Scope |
|---|---|---|
| focused | Answer a specific question | One decision: "CodeMirror vs ProseMirror?" — targeted search, local scan, 1-2 comparisons. Produces a 1-page recommendation. |
| wide | Understand the space | Landscape for a new product or feature. Competitors, ecosystem, user needs, architecture options. Enough to write a spec. |
| deep | Plan a major build | Leave no stone unturned. Everything in wide PLUS library/component research, plugin ecosystems, GitHub issues mining, community sentiment, future-casting, technical deep-dives on every decision. Enough to drive weeks of coding. |
Default: wide
Workflow
1. Understand the Intent
Ask the user:
- What are you building? (one sentence)
- Why? What problem does it solve? Who's it for?
- Constraints? Stack preferences, budget, timeline, must-haves?
- Existing work? Any projects to build on? Repos to look at?
If the user gives a brief prompt ("obsidian replacement on cloudflare"), that's enough — fill in the gaps through research.
2. Local Exploration
Scan the user's machine for relevant prior work:
# Find related projects by name/keyword
ls ~/Documents/ | grep -i "KEYWORD"
# Read CLAUDE.md of related projects for architecture context
find ~/Documents -maxdepth 2 -name "CLAUDE.md" -exec grep -l "KEYWORD" {} \;
# Check for reusable patterns, schemas, components
find ~/Documents -maxdepth 3 -name "schema.ts" -o -name "ARCHITECTURE.md" | head -20
For each related project found:
- Read CLAUDE.md (stack, architecture, gotchas)
- Check for reusable code (schemas, components, utilities, configs)
- Note what worked well and what didn't (from git history, TODO comments)
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 · 316 lines · 126 tokens per session scan A eb46840e338a
deep-research is a skill published in the GitHub repository jezweb/claude-skills (999 stars, last pushed 2mo ago), licensed MIT. It adds 126 tokens to every session and 3,595 once invoked, about $0.0006 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
ensemble-solving
Generate multiple diverse solutions in parallel and select the best. Use for architecture decisions, code generation with multiple valid approaches, or creative tasks where exploring alternatives improves quality.
code-transfer
Transfer code between files with line-based precision. Use when users request copying code from one location to another, moving functions or classes between files, extracting code blocks, or inserting code at specific line numbers.
feature-planning
Break down feature requests into detailed, implementable plans with clear tasks. Use when user requests a new feature, enhancement, or complex change.
review-implementing
Process and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to implement suggestions from reviews.
code-auditor
Performs comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability. Use when user wants to audit code quality, identify technical debt, find security issues, assess test coverage, or get a codebase health check.
codebase-documenter
Generates comprehensive documentation explaining how a codebase works, including architecture, key components, data flow, and development guidelines. Use when user wants to understand unfamiliar code, create onboarding docs, document architecture, or explain how the system works.