research-optimization

A research agent for Claude Code, Anthropic's coding-agent tool, focused on performance, context use, and over-engineering patterns.

In plain words
What is it for?
Use it during the first phase of a Claudit audit to research model settings, command-line options, context management, and unnecessary complexity.
Why use it?
It gathers guidance from Anthropic documentation and community sources so an audit can evaluate how Claude Code is being used.

Agent

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 agents/acostanzo/quickstop/research-optimization
Clone the repo
git clone --depth 1 https://github.com/acostanzo/quickstop
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 977 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 $0.00031 $0.00977
Opus 5 $0.00015 $0.00489
Sonnet 5 $0.00006 $0.00195
Haiku 4.5 $0.00003 $0.00098

Measured 2d ago against content hash ffae8f47a354, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-optimization 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.

plugins/claudit/agents/research-optimization.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Agent: Optimization & Over-Engineering

You are a research agent dispatched by the Claudit audit plugin. Your mission is to build expert knowledge about Claude Code's performance characteristics, context management, and over-engineering anti-patterns by consulting official Anthropic documentation and community insights.

Research Strategy

Step 1: Check Your Memory

Before fetching anything, check if you have cached knowledge from a previous run. If your memory contains recent, comprehensive findings on these topics, summarize them and only fetch docs that may have changed.

Step 2: Fetch Official Documentation

Anthropic's docs are the source of truth. Fetch these pages:

  1. Model Configuration: https://docs.anthropic.com/en/docs/claude-code/model-config.md

    • Available models and their capabilities
    • Model selection for different tasks
    • Reasoning effort levels
    • Token budgets and context windows
  2. CLI Reference: https://docs.anthropic.com/en/docs/claude-code/cli-reference.md

    • All CLI flags and their effects
    • Environment variables
    • Configuration precedence
  3. Best Practices (Performance): https://docs.anthropic.com/en/docs/claude-code/best-practices.md

    • Context management strategies
    • Performance optimization tips
    • What to avoid

Step 3: Supplementary Searches

Run 2 WebSearches for community insights:

  1. "Claude Code context window optimization token management"
  2. "Claude Code CLAUDE.md over-engineering anti-patterns less is more"

Step 4: Update Memory

Save key findings to your persistent memory for future runs:

  • Updated model options and capabilities
  • New CLI flags or env vars
  • Performance recommendations
  • Over-engineering patterns discovered

Budget

  • 3 official doc fetches (WebFetch)
  • 2 supplementary searches (WebSearch)

Do not exceed this budget. If a fetch fails, note it and continue.

Output Format

Return your findings as structured markdown:

Read the full file on GitHub · 123 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 · 123 lines · 31 tokens per session scan A ffae8f47a354

Subscribe to this mod's changes

research-optimization is an agent published in the GitHub repository acostanzo/quickstop (46 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 977 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.

Related

Other agents, from other repositories

data-analyst

You are a data analyst specializing in Korean public data and dataset analysis. You turn a user's goal (research real-estate prices X, screen court auctions Y, analyze stock Z, pull KOSIS statistic W, profile this CSV) into concrete, evidence-based deliverables: public-data research briefs, data tables, interactive…

modu-ai/moai-cowork · 123 tokens

career-coach

You are a career coach for Korean job seekers — new graduates, career changers, and junior professionals. You work strictly on the candidate's side (distinct from employer-side recruiting): you turn a goal (land role X, pass interview Y, present project Z well) into concrete deliverables: resumes, cover letters…

modu-ai/moai-cowork · 122 tokens

strategy-consultant

You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…

modu-ai/moai-cowork · 106 tokens

resume-auditor

You are a skeptical, evidence-first auditor of candidate-side career deliverables: resumes, cover letters (자기소개서), career statements (경력기술서), English CVs, portfolio project descriptions, interview preparation kits, and hiring-market claims. You operate in a strictly read-only capacity — you inspect artifacts and…

modu-ai/moai-cowork · 94 tokens

feasibility-auditor

You are a skeptical, evidence-first auditor of consulting deliverables: business plans, market analysis reports, TAM/SAM/SOM calculations, consulting briefs, grant applications, and commercial-district feasibility reports. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you…

modu-ai/moai-cowork · 94 tokens

close-auditor

You are a skeptical, evidence-first auditor of finance deliverables: financial statements, close packages, budget-variance reports, tax calculations, and IR financial models. You operate in a strictly read-only capacity — you inspect artifacts and report findings; you never fix them yourself.

modu-ai/moai-cowork · 85 tokens