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.
npx agentmods add commands/achitokun14/claude-universal/researchgit clone --depth 1 https://github.com/Achitokun14/claude-universalWrote 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.
[](https://agentmods.dev/commands/achitokun14/claude-universal/research)<a href="https://agentmods.dev/commands/achitokun14/claude-universal/research"><img src="https://agentmods.dev/badge/commands/achitokun14/claude-universal/research.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.00406 |
| Opus 5 | $0.00013 | $0.00203 |
| Sonnet 5 | $0.00005 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00041 |
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 5d 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.
What it actually says
Run a parallel research pass on $ARGUMENTS and produce a cited brief.
Steps:
-
If
$ARGUMENTSis empty, ask: "What's the research topic?". -
Dispatch these calls in parallel (single message, multiple tool calls):
WebSearchfor$ARGUMENTS(broad)mcp__duckduckgo__duckduckgo_web_searchfor$ARGUMENTS(cross-check)- If the topic mentions a library/framework/SDK, also:
mcp__plugin_context7_context7__resolve-library-idthenquery-docs
-
From the search results, pick the top 3-5 distinct, high-quality URLs and dispatch parallel
WebFetchon each (prompt: "Extract: main claim, key data points, limitations, date published, author credibility."). -
Synthesize into this format:
# Research: $ARGUMENTS **Date:** YYYY-MM-DD | **Sources consulted:** N ## TL;DR <3-bullet summary> ## Key findings - <claim> — <source 1> - <claim> — <source 2> ... ## Contradictions / gaps - <where sources disagree or are silent> ## Sources 1. <title> — <url> — <date> — <credibility note> 2. ... -
Offer to save the brief to
~/Desktop/ACTIVITIES/llm-wiki/research/<slug>-$(date +%Y%m%d).md.
Never present unsourced claims as fact. If context7 has docs on the topic, cite them first.
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.
- 5d ago First seen · 45 lines · 26 tokens per session scan A 9a5e239f6f59
research is a command published in the GitHub repository Achitokun14/claude-universal (2 stars, last pushed 2mo ago), licensed MIT. It adds 26 tokens to every session and 406 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.
Other commands, from other repositories
dev-screenshot
Use the dev screenshot script to iterate on UI changes. This builds the Go server with dev tags, starts it on an isolated port, opens the browser, and captures a screenshot for visual verification.
publish
Publish a new release of Coral to PyPI. The user provides the version number as $ARGUMENTS (e.g. "2.2.0").
init
Initialize configurations for Supabase local development.
milestone-list
PitWay: List every milestone with a concise one-line status.
setup
Install the claude-pace statusline bundled with this plugin.
fix
Universal debugging and fix application with semantic code analysis.