Nav Deep Research

What it does

When your agent uses it

• Says deep research on
• Research the web for
• Write a research report on
• What does the literature say about

Example prompts

• “deep research on”
• “research the web for”
• “write a research report on”
• “/nav-deep-research”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, WebSearch, WebFetch, Task

Workflow steps

2 steps, taken from the step headings in SKILL.md.

1. 1enabled check and paths (run before anything else)
2. 25: new run or resume

What it can do on your machine

Read from SKILL.md and the folder at commit 3bb9eac. 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:

  • Read
  • Write
  • Edit
  • Bash
  • WebSearch
  • WebFetch
  • Task

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Python), 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 no API keys, tokens, secrets or passwords.

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

Context cost

Nav Deep Research loads about 2k tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 787 words of instructions outside code blocks.

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

~107

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

~2k

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

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

  allowed-tools: Read, Write, Edit, Bash, WebSearch, WebFetch, Task

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from qf-studio/navigator at commit 3bb9eac, republished under its MIT licence (© qf-studio). 787 words, ~1,967 tokens.

name

nav-deep-research

description

Web deep research producing a cited report from fetched sources, adversarially reviewed and gate-checked, with conclusions ingested into the knowledge graph. Auto-invoke when user says "deep research on", "research the web for", "write a research report on", "what does the literature say about", or "deep dive into" a topic outside the codebase. For codebase questions use the navigator-research agent instead.

allowed-tools

Read, Write, Edit, Bash, WebSearch, WebFetch, Task

version

1.1.0

python3 - <<'EOF'
import json, pathlib
cfg = json.loads(pathlib.Path(".agent/.nav-config.json").read_text()) if pathlib.Path(".agent/.nav-config.json").exists() else {}
d = cfg.get("deep_research") or {}
print(json.dumps({"enabled": bool(d.get("enabled", False)), "config": d}))
EOF

Deep research is off. Enable it with: "enable deep_research"
(or set deep_research.enabled: true in .agent/.nav-config.json). Ships off because a
run fetches dozens of third-party pages and spends several opus subagent calls.

PLUGIN_DIR="${CLAUDE_PLUGIN_ROOT:-$(cat "${NAVIGATOR_CONFIG_HOME:-${XDG_CONFIG_HOME:-$HOME/.config}/navigator}/plugin-root" 2>/dev/null)}"
[ -d "$PLUGIN_DIR/skills" ] || PLUGIN_DIR="$HOME/.claude/plugins/marketplaces/navigator-marketplace"
NDR=""
for cand in "$PLUGIN_DIR/skills/nav-deep-research/functions" "$PWD/skills/nav-deep-research/functions"; do
  [ -f "$cand/research_run.py" ] && NDR="$cand" && break
done
echo "NDR_FUNCTIONS=$NDR"

python3 "$NDR/research_run.py" init --query "<the user's prompt, verbatim>"

python3 "$NDR/research_run.py" resume --run <slug>

hyperresearch is installed here. Run it for the full pipeline:
  /hyperresearch <the same query>
When it finishes, say "resume research <slug> at step 6" and I will ingest its
research/notes/final_report_*.md into the knowledge graph.

© qf-studio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 17 other files in skills/nav-deep-research of qf-studio/navigator.

• SKILL.md
• functions/report_parse.py
• functions/report_to_graph.py
• functions/research_run.py
• functions/ship_gate.py
• functions/source_store.py
• functions/test_report_to_graph.py
• functions/test_research_run.py
• functions/test_ship_gate.py
• functions/test_source_store.py
• functions/untrusted.py
• reference/REPORT-FORMAT.md
• steps/1-decompose.md
• steps/2-sweep.md
• steps/3-draft.md
• steps/4-critique.md
• steps/5-patch.md
• steps/6-ship.md

Open the folder on GitHubat commit 3bb9eac