ctx:research

ctx:research is a command for coding agents from shakestzd/contextune. It costs 25 tokens per session (1,800 once invoked), scanned A, original, MIT.

A research command that asks three separate agents to investigate a technical question from different angles: current web information, your codebase, and installed dependencies.

In plain words
What is it for?
Use it to compare libraries or API approaches, check current testing options, or find out whether your project already supports a feature such as authentication.
Why use it?
It reduces the need to search documentation, inspect code, and check compatibility separately. The results are combined into a comparison and suggested next steps.

Command

Part of the contextune plugin — 8 skills, 14 commands, 5 agents, 6 hooks, 1 MCP server 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/shakestzd/contextune/ctx-research
Clone the repo
git clone --depth 1 https://github.com/shakestzd/contextune

Or install contextune, the plugin that ships this one along with the rest of its 8 skills, 14 commands, 5 agents, 6 hooks, 1 MCP server.

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 ctx:research

README.md
[![agentmods](https://agentmods.dev/badge/commands/shakestzd/contextune/ctx-research.svg)](https://agentmods.dev/commands/shakestzd/contextune/ctx-research)
Your own site
<a href="https://agentmods.dev/commands/shakestzd/contextune/ctx-research"><img src="https://agentmods.dev/badge/commands/shakestzd/contextune/ctx-research.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,800 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 $0.00025 $0.01800
Opus 5 $0.00013 $0.00900
Sonnet 5 $0.00005 $0.00360
Haiku 4.5 $0.00003 $0.00180

Measured 4d ago against content hash 9aace4cdd103, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ctx: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 4d 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.

commands/ctx-research.md · 282 lines

How it starts

The opening of the file, as written. The whole thing — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contextune Research - Quick Technical Investigation

Conduct focused research using 3 parallel Haiku agents to answer specific technical questions quickly.

Use Cases

  • "What's the best React state library in 2025?"
  • "Should I use REST or GraphQL for this API?"
  • "What testing frameworks work with Python 3.12?"
  • "Does our codebase already handle authentication?"

How It Works

  1. You ask a research question
  2. 3 parallel agents execute (1-2 min total):
    • Agent 1: Web Research - Latest trends, comparisons, best practices
    • Agent 2: Codebase Search - Existing patterns, reuse opportunities
    • Agent 3: Dependency Analysis - What's installed, compatibility
  3. Synthesis - Combined findings with recommendation
  4. Result - Comparison table + actionable next steps

Agent Specifications

Agent 1: Web Research

Searches the web for current information:

Research {QUESTION} using WebSearch.

Current date: {CURRENT_DATE}
Tech stack: {TECH_STACK}

Search queries:
- '{QUESTION} best practices {CURRENT_YEAR}'
- '{QUESTION} comparison latest'
- '{QUESTION} recommendations {CURRENT_YEAR}'

Report format (<500 words):
1. **Top 3 Options Found**
2. **Comparison Table** (pros/cons for each)
3. **Current Trends** (what's popular/recommended)
4. **Recommendation** with reasoning

Focus on recent information (2024-2025 preferred).

Expected output: Comparison of top solutions with pros/cons


Agent 2: Codebase Search

Searches existing code for patterns:

Search codebase for existing solutions to {QUESTION}.

Use Grep/Glob to find:
- Similar functionality: grep -r '{KEYWORDS}' .
- Relevant files: glob '**/*{pattern}*'
- Existing implementations

**CRITICAL**: If similar code exists, recommend REUSING it!

Report format (<400 words):
1. **Existing Functionality** (file:line references)
2. **Patterns to Follow** (coding style, architecture)
3. **Recommendation**:
   - REUSE: If good solution exists
   - NEW: If nothing suitable found
   - ENHANCE: If partial solution exists

Include specific file paths and line numbers.

Read the full file on GitHub · 282 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. 4d ago First seen · 282 lines · 25 tokens per session scan A 9aace4cdd103

Subscribe to this mod's changes

ctx:research is a command published in the GitHub repository shakestzd/contextune (5 stars, last pushed 8mo ago), licensed MIT. It adds 25 tokens to every session and 1,800 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 2026-08-31.