research

A command for researching a question or topic by searching for sources, collecting them, and compiling the findings into wiki articles. It can also compare evidence for and against a specific claim.

In plain words
What is it for?
Use it for deep topic research, thesis-style evidence reviews, new topic wikis, source collection, and research performed in a local project wiki.
Why use it?
It organizes a multi-step research process and keeps the resulting sources and conclusions in a chosen topic wiki instead of leaving them as scattered notes.

Command

Part of the claude-plugin plugin — 1 skill, 28 commands shipped together

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 commands/nvk/llm-wiki/research
Clone the repo
git clone --depth 1 https://github.com/nvk/llm-wiki

Or install claude-plugin, the plugin that ships this one along with the rest of its 1 skill, 28 commands.

Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,264 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 $0.00047 $0.09264
Opus 5 $0.00023 $0.04632
Sonnet 5 $0.00009 $0.01853
Haiku 4.5 $0.00005 $0.00926

Measured 3d ago against content hash 1407f9396621, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

claude-plugin/commands/research.md · 678 lines

How it starts

The opening of the file, as written. The whole thing — 678 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Your task

Conduct deep research on the topic in $ARGUMENTS. This is an automated pipeline: search → ingest → compile.

Parse $ARGUMENTS

  • topic/question: The research subject — everything that is not a flag. Auto-detected as topic vs question (see Input Detection below).
  • --mode thesis "": Activate thesis mode. The claim is the scope constraint — sources that don't relate to it are skipped. Agents evaluate evidence for/against. A verdict is rendered at the end. See Thesis Research Mode below.
  • --new-topic: Create a new topic wiki from the topic name and start researching into it. Works from any directory. Derives the wiki slug from the topic (e.g., "quantum error correction" → quantum-error-correction).
  • --sources : Target sources PER ROUND (default: 5, max: 20)
  • --deep: 8 parallel agents with broader search angles
  • --retardmax: 10 agents, skip planning, ingest aggressively
  • --min-time : Minimum research time. Keep running research rounds until this duration is reached. Formats: 30m, 1h, 2h, 4h. Default: single round (no minimum).
  • --wiki : Target a specific existing topic wiki
  • --local: Use project-local .wiki/
  • --plan: Decompose the topic into 3-5 independent research paths, present the plan for confirmation, then execute all paths in parallel. Each path gets its own agent group (5 agents standard, 8 with --deep). Ingest runs in parallel across paths (each path writes unique raw files); compilation runs once after all paths complete (single pass sees all sources for better cross-referencing). Without --plan, research runs a single path as before. See Plan Mode below.
  • --project : Tag all new outputs with this project. The research playbook/summary artifact is saved inside output/projects/<slug>/ instead of flat output/. Compiled wiki articles get project: <slug> frontmatter. If the project doesn't exist, fail early with a helpful error. See references/projects.md for the projects architecture.
  • --include-archived: Explicitly allow researching into an archived target wiki. Keep the target archived and label the session accordingly.
  • --specialist : Explicitly apply an enabled personal specialist; repeat up to three times. For project-local .wiki/, explicit selection is required because v1 has no persisted local-project allowlist.
  • --no-specialists: Run the baseline research workflow without reading specialist package bodies. Mutually exclusive with --specialist.

Read the full file on GitHub · 678 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. 3d ago First seen · 678 lines · 47 tokens per session scan A 1407f9396621

Subscribe to this mod's changes

research is a command published in the GitHub repository nvk/llm-wiki (1,175 stars, last pushed 6d ago), licensed MIT. It adds 47 tokens to every session and 9,264 once invoked, about $0.0002 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.