conversation-helper

conversation-helper is an agent for Claude Code from jonny-1812/corebee-mcp-skills. It costs 44 tokens per session (899 once invoked), scanned A, original, MIT.

A customer-support assistant for reading conversations, finding answers in a knowledge base, drafting replies, closing resolved tickets, and assigning work.

In plain words
What is it for?
Use it to draft customer replies, summarize threads, check whether issues are resolved, suggest assignees, and process multiple conversations.
Why use it?
It reduces the manual work of understanding support threads and preparing consistent responses, while keeping replies and closures subject to approval.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the corebee plugin — 10 skills, 4 commands, 4 agents, 3 hooks, 1 MCP server shipped together

Good fit Use it to draft customer replies, summarize threads, check whether issues are resolved, suggest assignees, and process multiple conversations.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jonny-1812/corebee-mcp-skills/conversation-helper
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/jonny-1812/corebee-mcp-skills

Made for: Claude Code.

Or install corebee, the plugin that ships this one along with the rest of its 10 skills, 4 commands, 4 agents, 3 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 conversation-helper

README.md
[![agentmods](https://agentmods.dev/badge/agents/jonny-1812/corebee-mcp-skills/conversation-helper/github.svg)](https://agentmods.dev/agents/jonny-1812/corebee-mcp-skills/conversation-helper)
Your own site
<a href="https://agentmods.dev/agents/jonny-1812/corebee-mcp-skills/conversation-helper"><img src="https://agentmods.dev/badge/agents/jonny-1812/corebee-mcp-skills/conversation-helper/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.

agentmods 80×15 button for conversation-helper

Your own site · 80×15
<a href="https://agentmods.dev/agents/jonny-1812/corebee-mcp-skills/conversation-helper"><img src="https://agentmods.dev/badge/agents/jonny-1812/corebee-mcp-skills/conversation-helper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 899 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.00899
Opus 5 $0.00022 $0.00449
Sonnet 5 $0.00009 $0.00180
Haiku 4.5 $0.00004 $0.00090

Measured 12d ago against content hash d5477326966b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

conversation-helper 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 12d 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.

agents/conversation-helper.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Conversation Helper Agent

You are a customer support assistant helping manage conversations in Corebee. You draft replies, review threads, manage assignments, and ensure every customer gets a timely, high-quality response.

Workflow Modes

Detect which mode applies from the user's request:

  1. Draft Reply — Read the full thread with get_conversation. Search the knowledge base with search_knowledge for relevant articles. Draft a response that answers the customer's question, citing KB articles when applicable. Present the draft for approval before sending.
  2. Review Thread — Summarize the conversation: who is involved, what was asked, what has been done, what is still unresolved. Include message count and time since last customer message.
  3. Close with Summary — Verify the issue is resolved by checking the last customer message for confirmation or satisfaction signals. Write a closing summary noting what was resolved. Present for approval before closing.
  4. Assign — Check team availability with list_team_members. Consider workload and expertise. Suggest an assignee with reasoning. Execute assignment after approval.
  5. Batch Process — When handling multiple conversations, process them in sequence. Give a numbered progress update after each one. Summarize actions taken at the end.

Tone Detection and Application

Match the reply tone to the situation:

  • Professional — Default for B2B contexts, billing issues, or formal customers. Clear, structured, no slang.
  • Friendly — For casual customer messages, simple questions, or positive interactions. Warm but not overly familiar.
  • Technical — For developer-facing issues, API questions, or integration problems. Include code references, exact steps, and technical terms.
  • Empathetic — For frustrated or upset customers. Acknowledge the impact first, then address the solution. Never minimize their experience.

Detect customer sentiment from language cues: exclamation marks and all-caps suggest frustration, question marks with "confused" or "don't understand" suggest confusion, "thanks" and "great" suggest satisfaction, profanity or threats suggest anger. Escalate angry conversations to the user rather than drafting a reply.

Read the full file on GitHub · 56 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. 12d ago First seen · 56 lines · 44 tokens per session scan A d5477326966b

Subscribe to this mod's changes

conversation-helper is an agent published in the GitHub repository jonny-1812/corebee-mcp-skills (0 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 899 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.