Deep Research

What it does

When your agent uses it

• Tasks that involve Deep research
• Tasks that involve Web search

Example prompts

• “/deep-research”

Requirements

• Python 3
• A credential in OPENAI_API_KEY
• A credential in PERPLEXITY_API_KEY
• Pre-approved tools (allowed-tools): Bash, Read, Write, AskUserQuestion, WebSearch

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Immediately tell the user with a WARNING: prefix — which providers failed, their error messages, and elapsed time
2. 2You SHOULD supplement failed providers with WebSearch to fill knowledge gaps
3. 3Note which findings in your synthesis came from WebSearch rather than deep research

What it can do on your machine

Read from SKILL.md and the folder at commit dfbdd82. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • Write
  • AskUserQuestion
  • WebSearch

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 11 files in scripts/ (Python, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • python3

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • OPENAI_API_KEY
  • PERPLEXITY_API_KEY
  • GEMINI_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deep Research loads about 3.1k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 781 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~46

When it runs · the whole SKILL.md, loaded when a task matches

~3.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:16

  s at least one API key. Check `~/.claude/.env`:

• NoteMentions a .env fileSKILL.md:23

  cat > ~/.claude/.env << 'ENVEOF'

• NoteMentions a .env fileSKILL.md:37

  chmod 600 ~/.claude/.env

• NoteMentions a .env fileSKILL.md:38

  echo "Config created at ~/.claude/.env"

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, Write, AskUserQuestion, WebSearch

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 781 words (~3,083 tokens).

name

deep-research

allowed-tools

Bash, Read, Write, AskUserQuestion, WebSearch

argument-hint

[research topic or question]

context

fork

agent

general-purpose

Read the full SKILL.md on GitHub

Files

SKILL.md and 22 other files (scripts) in skills/deep-research of juanandresgs/claude-ctrl.

• SKILL.md
• .gitignore
• fixtures/gemini_sample.json
• fixtures/openai_sample.json
• fixtures/perplexity_sample.json
• scripts/deep_research.py
• scripts/lib/__init__.py
• scripts/lib/env.py
• scripts/lib/errors.py
• scripts/lib/gemini_dr.py
• scripts/lib/http.py
• scripts/lib/matrix.py
• scripts/lib/openai_dr.py
• scripts/lib/perplexity_dr.py
• scripts/lib/render.py
• scripts/lib/validate.py
• tests/__init__.py
• … and 6 more

Open the folder on GitHubat commit dfbdd82