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 agentmods add skills/keysersoose/claude-code-setup/deep-researchnpx skills add keysersoose/claude-code-setup --skill deep-researchgit clone --depth 1 https://github.com/keysersoose/claude-code-setupWrote 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/keysersoose/claude-code-setup/deep-research)<a href="https://agentmods.dev/skills/keysersoose/claude-code-setup/deep-research"><img src="https://agentmods.dev/badge/skills/keysersoose/claude-code-setup/deep-research.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.02120 |
| Opus 5 | $0.00036 | $0.01060 |
| Sonnet 5 | $0.00014 | $0.00424 |
| Haiku 4.5 | $0.00007 | $0.00212 |
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 3d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research
Overview
Use this skill for research where claims must be traceable to sources. It is harness-neutral, but the default discovery-to-capture path is explicit: use sibling advanced-web-search/scripts/opencli_google_search.py to save candidate URLs as JSON, then use this skill's scripts/batch_capture.py --search-json to crawl them with Crawl4AI, then read the raw markdown and write the final brief.
Runtime requirement: Crawl4AI must be installed for raw capture. Install with python -m pip install -U crawl4ai, then run crawl4ai-setup and crawl4ai-doctor. See ../crawl4ai/SKILL.md.
Operating Contract
- Prefer official, primary, and direct sources.
- Use multiple targeted query classes, not one broad query.
- Treat search snippets as leads, not evidence.
- Inspect extraction quality; do not treat HTTP success as content success.
- Separate facts, interpretation, recommendations, counter-evidence, open questions, and confidence.
- Cite material claims with URLs or local raw/source artifact paths.
- Label blocked, partial, old, borderline, and inferred evidence.
- For durable research, write artifacts in the Hermes Obsidian layout, not a generic flat folder.
Workflow
Phase 0: Scope
Restate the question, decision target, constraints, time window, output format, and source classes needed. Ask a concise clarifying question only if ambiguity changes the source universe or tool calls materially.
Completion: scope is clear enough to define at least four query classes.
Phase 1: Discovery
Use advanced-web-search/scripts/opencli_google_search.py when it is available. Do not use a harness built-in web search as the primary discovery step when OpenCLI is available. Read references/query-patterns.md when constructing the search plan.
Always save discovery output to a JSON file with --output:
python ../advanced-web-search/scripts/opencli_google_search.py \
--query "Hybrid XBRL tagging after:2026-03-01" \
--query "site:github.com XBRL AI tagging after:2026-03-01" \
--max-results 30 \
--pages 8 \
--output outputs/hybrid_xbrl_sources.json
What ships with it
10 files 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.
- agents/openai.yaml 207 B
- references/obsidian-layout.md 3.1 KB
- references/query-patterns.md 1.8 KB
- references/source-quality-rubric.md 1.9 KB
- scripts/__pycache__/batch_capture.cpython-310.pyc 22 KB
- scripts/batch_capture.py 25 KB runs code
- scripts/test_batch_capture.py 11 KB runs code
- templates/research-brief.md 1.3 KB
- templates/source-index.md 1.4 KB
- templates/source-note.md 800 B
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.
- 3d ago First seen · 174 lines · 71 tokens per session scan A 74674bafa4b0
deep-research is a skill published in the GitHub repository keysersoose/claude-code-setup (2 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 2,120 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…