research

research is a command for Claude Code from cloudrepo-io/founder-os. It costs 10 tokens per session (740 once invoked), scanned A, original, MIT.

A command for adding a research or investigation task to a project's work queue. The task is intended to produce a plan document before implementation begins.

In plain words
What is it for?
Use it to queue research about possible approaches, unclear scope, affected files or systems, and the expected contents of an implementation plan.
Why use it?
It separates questions that need investigation, comparison, or architecture decisions from work that is already fully specified for coding.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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/cloudrepo-io/founder-os/research
Clone the repo
git clone --depth 1 https://github.com/cloudrepo-io/founder-os

Made for: Claude Code.

Wrote 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.

agentmods badge for research

README.md
[![agentmods](https://agentmods.dev/badge/commands/cloudrepo-io/founder-os/research.svg)](https://agentmods.dev/commands/cloudrepo-io/founder-os/research)
Your own site
<a href="https://agentmods.dev/commands/cloudrepo-io/founder-os/research"><img src="https://agentmods.dev/badge/commands/cloudrepo-io/founder-os/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 740 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 5.1 $0.00010 $0.00740
Opus 5 $0.00005 $0.00370
Sonnet 5 $0.00002 $0.00148
Haiku 4.5 $0.00001 $0.00074

Measured 6d ago against content hash 00e322ab5b87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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/commands/queue/research.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Research Task to Queue

Add a research or investigation task that produces a plan document before implementation begins.

Arguments

  • $ARGUMENTS - Brief description of what needs to be researched

When to Use

Use /queue:research instead of /queue:add when:

  • The task requires investigation before implementation
  • You need to evaluate multiple approaches
  • The scope is unclear and needs a plan first
  • Architecture decisions need to be documented
  • The change is significant enough to warrant review before coding

Process

  1. Read .claude/queue/backlog.json to get current items

  2. Gather required information:

    • Title: From the arguments (or ask if unclear)
    • Priority: 1 (urgent) to 5 (low) - ask if not specified
    • Owner: Which agent should investigate (e.g., staff-engineer, staff-software-architect)
    • Research Question: What needs to be investigated
    • Scope: What areas/files/systems are involved
    • Expected Output: What the plan document should cover
  3. Create the work item:

    {
      "id": "YYYY-MM-DD-{slug}",
      "title": "Research: Brief description",
      "type": "research",
      "priority": 1-5,
      "status": "pending",
      "requires_approval": true,
      "owner": "agent-type",
      "plan_file": ".claude/queue/plans/YYYY-MM-DD-{slug}.md",
      "context": {
        "problem": "What needs investigating",
        "research_questions": ["Question 1", "Question 2"],
        "scope": ["area1", "area2"],
        "expected_output": "What the plan should cover"
      },
      "sizing": "single-context",
      "created": "ISO timestamp",
      "updated": "ISO timestamp"
    }
    
  4. Add to backlog.json and write the file

Plan File Template

When the research task is picked up via /queue:work, the agent will create a plan document at the plan_file path using this structure:

# Plan: {title}

**Research Task**: {id}
**Author**: {owner}
**Date**: {date}

## Problem Statement
{What we're trying to solve}

## Investigation Summary
{What was discovered during research}

## Proposed Approach
{Recommended solution with rationale}

## Alternatives Considered
| Approach | Pros | Cons |
|----------|------|------|
| {alt1} | ... | ... |
| {alt2} | ... | ... |

## Implementation Plan
1. {Step 1}
2. {Step 2}
3. {Step 3}

## Files Affected
- {file1}: {what changes}
- {file2}: {what changes}

## Risks & Mitigations
- {risk1}: {mitigation}

## Open Questions
- {Any remaining unknowns}

Read the full file on GitHub · 118 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. 6d ago First seen · 118 lines · 10 tokens per session scan A 00e322ab5b87

Subscribe to this mod's changes

research is a command published in the GitHub repository cloudrepo-io/founder-os (19 stars, last pushed 7mo ago), licensed MIT. It adds 10 tokens to every session and 740 once invoked, about $0.0001 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.