research

A research command that investigates a question across connected company sources and combines the findings with source attribution.

In plain words
What is it for?
Use it to answer customer questions, investigate reported issues, research a product or topic, and review an account's history.
Why use it?
It reduces the need to search separate documents, storage systems, customer records, and other sources manually while keeping track of where information came from.

Command

Part of the customer-support plugin — 4 skills, 5 commands 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/fergupa/claude_plugins/research
Clone the repo
git clone --depth 1 https://github.com/fergupa/claude_plugins

Or install customer-support, the plugin that ships this one along with the rest of its 4 skills, 5 commands.

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 930 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 $0.00012 $0.00930
Opus 5 $0.00006 $0.00465
Sonnet 5 $0.00002 $0.00186
Haiku 4.5 $0.00001 $0.00093

Measured 2d ago against content hash 19e0cdcc2174, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

customer-support/commands/research.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Multi-source research on a customer question, product topic, or account-related inquiry. Synthesizes findings from all available sources with clear attribution.

Usage

/research <question or topic>

Workflow

1. Parse the Research Request

Identify what type of research is needed:

  • Customer question: Something a customer has asked that needs an answer (e.g., "Does our product support SSO with Okta?")
  • Issue investigation: Background on a reported problem (e.g., "Has this bug been reported before? What's the known workaround?")
  • Account context: History with a specific customer (e.g., "What did we tell Acme Corp last time they asked about this?")
  • Topic research: General topic relevant to support work (e.g., "Best practices for webhook retry logic")

2. Search Available Sources

Search in priority order, adapting to what is connected:

Tier 1 — Internal Documentation (highest confidence):

  • ~~knowledge base (if connected): product docs, runbooks, FAQs
  • ~~cloud storage: internal documents, specs, guides, past research
  • ~~CRM notes: previous answers to similar questions, account context

Tier 2 — Team Communications:

  • ~~chat: search for the topic in relevant channels; check if teammates have discussed or answered this before
  • ~~email: search for previous correspondence on this topic
  • ~~support platform (if connected): check if this has been asked/resolved before

Tier 3 — External Sources:

  • Web search: official documentation, blog posts, community forums
  • Public knowledge bases, help centers, release notes

3. Synthesize Findings

Compile results into a structured research brief:

## Research: [Question/Topic]

### Answer
[Clear, direct answer to the question — lead with the bottom line]

**Confidence:** [High / Medium / Low]
[Explain what drives the confidence level]

### Key Findings

**From [Source 1]:**
- [Finding with specific detail]
- [Finding with specific detail]

**From [Source 2]:**
- [Finding with specific detail]

### Context & Nuance
[Any caveats, edge cases, or additional context that matters]

### Sources
1. [Source name/link] — [what it contributed]
2. [Source name/link] — [what it contributed]
3. [Source name/link] — [what it contributed]

### Gaps & Unknowns
- [What couldn't be confirmed]
- [What might need verification from a subject matter expert]

### Recommended Next Steps
- [Action if the answer needs to go to a customer]
- [Action if further research is needed]
- [Who to consult for verification if needed]

Read the full file on GitHub · 117 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 · 117 lines · 12 tokens per session scan A 19e0cdcc2174

Subscribe to this mod's changes

research is a command published in the GitHub repository fergupa/claude_plugins (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 930 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.