research

A structured process for investigating technical questions, comparing technologies, or exploring a possible solution before committing to it.

In plain words
What is it for?
Use it for technical investigations, technology evaluations, architecture spikes, and research linked to an issue or ticket.
Why use it?
It keeps research focused on evidence and a specific decision instead of producing unsupported recommendations or unnecessary code. It also records findings from exploratory work.

Command for Claude Code

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/qwickapps/ai-sdlc-workflows/research
Clone the repo
git clone --depth 1 https://github.com/qwickapps/ai-sdlc-workflows

Made for: Claude Code.

Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 874 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 $0.00005 $0.00874
Opus 5 $0.00003 $0.00437
Sonnet 5 $0.00001 $0.00175
Haiku 4.5 $0.00001 $0.00087

Measured 2d ago against content hash 50f9c04ac067, 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 2d 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/.claude/commands/research.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical Research Workflow

You are now in Technical Research Mode. Use this for research and investigation tasks.

Input: $ARGUMENTS (question to answer, technology to evaluate, or problem to investigate)

CRITICAL RULES

  1. Research first, recommend second - gather evidence before opinions (see RESEARCH-DEPTH.md)
  2. Document findings - spikes produce knowledge, not just code
  3. Time-box appropriately - spikes should answer specific questions
  4. When blocked - STOP and discuss (see COMMUNICATION-PROTOCOL.md)
  5. Use proper research tools - Explore agent, QwickBrain MCP, Chrome (see RESEARCH-DEPTH.md)

Interactive Setup

Check if $ARGUMENTS is provided.

If $ARGUMENTS is empty, ask:

"What would you like me to investigate? Please describe:

  • The question or problem to research
  • Technologies or approaches to evaluate
  • What decision this will inform
  • Issue/ticket number (if this spike is tracked)"

Extract and store the issue/ticket number (if provided) for:

  • Document attachment
  • Optional branch naming if code exploration is needed

Wait for response before proceeding.

Workflow Phases

PHASE 1: Define Scope (Product Manager + Architect)

  1. Clarify the investigation:

    • What question(s) are we trying to answer?
    • What are the options to evaluate?
    • What criteria matter (performance, complexity, cost, etc.)?
    • What is the time box?
  2. GATE: Confirm scope with user before proceeding

WORKSPACE SETUP (Optional): Create Git Worktree

If the spike requires code exploration or POC implementation, set up an isolated workspace:

  1. Ask user: "This spike may require code changes. Should I create an isolated worktree for experimentation?"

  2. If yes, create git worktree:

    git worktree add ../worktrees/spike/<ISSUE-OR-NAME> -b spike/<ISSUE-OR-NAME>
    cd ../worktrees/spike/<ISSUE-OR-NAME>
    
  3. If no or not applicable: Continue without worktree (research only)

Note: Spike branches are typically exploratory and may not be merged. Document findings in the spike report instead.

Read the full file on GitHub · 112 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. 2d ago First seen · 112 lines · 5 tokens per session scan A 50f9c04ac067

Subscribe to this mod's changes

research is a command published in the GitHub repository qwickapps/ai-sdlc-workflows (2 stars, last pushed 5mo ago), licensed MIT. It adds 5 tokens to every session and 874 once invoked, about $0.0000 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.