A command for researching technical topics with a cache, which stores previous results for reuse. It supports researching, promoting, refreshing, and listing cached research.

Use it for commands such as researching a topic, refreshing expired material, promoting a result, or listing saved research.

It can reuse valid research instead of fetching the same topic again, while allowing outdated results to be refreshed.

research — Command for Claude Code by joaquimscosta

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.

Clone the repo

git clone --depth 1 https://github.com/joaquimscosta/arkhe-claude-plugins

Made for: Claude Code.

Or install core, the plugin that ships this one along with the rest of its 5 skills, 7 commands, 6 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/research/github.svg)](https://agentmods.dev/commands/joaquimscosta/arkhe-claude-plugins/research)

Your own site

<a href="https://agentmods.dev/commands/joaquimscosta/arkhe-claude-plugins/research"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/research/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/joaquimscosta/arkhe-claude-plugins/research"><img src="https://agentmods.dev/badge/commands/joaquimscosta/arkhe-claude-plugins/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 541 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00036	$0.00541
Opus 5	$0.00018	$0.00270
Sonnet 5	$0.00007	$0.00108
Haiku 4.5	$0.00004	$0.00054

Measured 9d ago against content hash 2a8501b72ee3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 9d 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/core/commands/research.md · 49 lines

What it actually says

Research

Arguments: $ARGUMENTS

Scripts: Glob for **/deep-research/scripts/cache_manager.py and use its parent directory as {scripts}.

Dispatch

Parse arguments to determine the operation:

Research (default — no keyword prefix)

Cache-first approach using a single fetch call:

Run: python3 {scripts}/cache_manager.py fetch "{topic}"
Parse the JSON output:
- exists=true, cache_status=valid: Present the content field to the user. Report cache HIT, path, expiration. Suggest /research promote {slug}.
- exists=true, expired=true: Present the content field. Warn: "Cache expired — returning cached content." Suggest /research refresh {slug}. Do NOT spawn agent.
- exists=false: Spawn deep-researcher agent (subagent_type: core:deep-researcher). Pass the topic and scripts path so the agent can cache results via cache_manager.py put.

Promote (`promote <slug>`)

Run: python3 {scripts}/promote.py {slug}
Parse JSON output. Report success path or error.

Refresh (`refresh <slug>`)

Spawn deep-researcher agent (subagent_type: core:deep-researcher).
Instruct it to: bypass cache, research fresh via EXA, cache with cache_manager.py put, then run promote.py {slug} --refresh if docs/research/{slug}.md exists.

List (`list [--all | --project <name>]`)

Run: python3 {scripts}/cache_manager.py list --format json [--all | --project <name>]
Scan docs/research/ for promoted entries.
Display as formatted markdown table with Cached (Tier 1) and Promoted (Tier 2) sections.

Cache Tiers

Tier 1 (User): ~/.claude/plugins/research/ — cross-project, 30-day TTL
Tier 2 (Team): docs/research/ — version controlled, editable

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.

9d ago First seen · 49 lines · 36 tokens per session scan A 2a8501b72ee3

Subscribe to this mod's changes

research is a command published in the GitHub repository joaquimscosta/arkhe-claude-plugins (21 stars, last pushed 25d ago), licensed MIT. It adds 36 tokens to every session and 541 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.

Claude Code Research ai-agents ai-developer-tools anthropic claude-code-agents claude-code-plugins

research

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Research

Dispatch

Research (default — no keyword prefix)

Promote (`promote <slug>`)

Refresh (`refresh <slug>`)

List (`list [--all | --project <name>]`)

Cache Tiers

What this file has done since we first saw it

Other commands, from other repositories

stats

permissions

merge

parallel

sandbox-promote

add-skill

research

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Research

Dispatch

Research (default — no keyword prefix)

Promote (promote <slug>)

Refresh (refresh <slug>)

List (list [--all | --project <name>])

Cache Tiers

What this file has done since we first saw it

Other commands, from other repositories

stats

permissions

merge

parallel

sandbox-promote

add-skill

Promote (`promote <slug>`)

Refresh (`refresh <slug>`)

List (`list [--all | --project <name>]`)