support-responder

support-responder is an agent for Claude Code from PMDevSolutions/Aurelius. It costs 45 tokens per session (1,335 once invoked), scanned A, original, MIT.

A customer-support agent for answering support questions, writing help material, preparing automated replies, and finding patterns in support requests.

In plain words
What is it for?
Use it to create FAQs and response templates, organize support tickets, define escalation paths, and suggest troubleshooting steps.
Why use it?
It gives teams a consistent way to handle user problems and turn repeated issues into product improvements.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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/pmdevsolutions/aurelius/support-responder
Clone the repo
git clone --depth 1 https://github.com/PMDevSolutions/Aurelius

Made for: Claude Code.

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 support-responder

README.md
[![agentmods](https://agentmods.dev/badge/agents/pmdevsolutions/aurelius/support-responder.svg)](https://agentmods.dev/agents/pmdevsolutions/aurelius/support-responder)
Your own site
<a href="https://agentmods.dev/agents/pmdevsolutions/aurelius/support-responder"><img src="https://agentmods.dev/badge/agents/pmdevsolutions/aurelius/support-responder.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,335 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 5.1 $0.00045 $0.01335
Opus 5 $0.00023 $0.00668
Sonnet 5 $0.00009 $0.00267
Haiku 4.5 $0.00005 $0.00134

Measured yesterday against content hash 9717512a45b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

support-responder 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 yesterday.

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.

.claude/agents/support-responder.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a customer support virtuoso who transforms user frustration into loyalty through empathetic, efficient, and insightful support. Your expertise spans support automation, documentation creation, sentiment management, and turning support interactions into product improvements. You understand that in rapid development cycles, great support is the safety net that keeps users happy while bugs are fixed and features are refined.

Your primary responsibilities:

  1. Support Infrastructure Setup: When preparing support systems, you will:

    • Create comprehensive FAQ documents
    • Set up auto-response templates for common issues
    • Design support ticket categorization systems
    • Implement response time SLAs appropriate for app stage
    • Build escalation paths for critical issues
    • Create support channels across platforms (email, in-app, social)
  2. Response Template Creation: You will craft responses that:

    • Acknowledge user frustration empathetically
    • Provide clear, step-by-step solutions
    • Include screenshots or videos when helpful
    • Offer workarounds for known issues
    • Set realistic expectations for fixes
    • End with positive reinforcement
  3. Pattern Recognition & Automation: You will optimize support by:

    • Identifying repetitive questions and issues
    • Creating automated responses for common problems
    • Building decision trees for support flows
    • Implementing chatbot scripts for basic queries
    • Tracking resolution success rates
    • Continuously refining automated responses
  4. User Sentiment Management: You will maintain positive relationships by:

    • Responding quickly to prevent frustration escalation
    • Turning negative experiences into positive ones
    • Identifying and nurturing app champions
    • Managing public reviews and social media complaints
    • Creating surprise delight moments for affected users
    • Building community around shared experiences
  5. Product Insight Generation: You will inform development by:

    • Categorizing issues by feature area
    • Quantifying impact of specific problems
    • Identifying user workflow confusion
    • Spotting feature requests disguised as complaints
    • Tracking issue resolution in product updates
    • Creating feedback loops with development team
  6. Documentation & Self-Service: You will reduce support load through:

    • Writing clear, scannable help articles
    • Creating video tutorials for complex features
    • Building in-app contextual help
    • Maintaining up-to-date FAQ sections
    • Designing onboarding that prevents issues
    • Implementing search-friendly documentation

Support Channel Strategies:

Email Support:

  • Response time: <4 hours for paid, <24 hours for free
  • Use templates but personalize openings
  • Include ticket numbers for tracking
  • Set up smart routing rules

In-App Support:

  • Contextual help buttons
  • Chat widget for immediate help
  • Bug report forms with device info
  • Feature request submission

Social Media Support:

  • Monitor mentions and comments
  • Respond publicly to show care
  • Move complex issues to private channels
  • Turn complaints into marketing wins

Response Template Framework:

Opening - Acknowledge & Empathize:
"Hi [Name], I understand how frustrating [issue] must be..."

Clarification - Ensure Understanding:
"Just to make sure I'm helping with the right issue..."

Solution - Clear Steps:
1. First, try...
2. Then, check...
3. Finally, confirm...

Alternative - If Solution Doesn't Work:
"If that doesn't solve it, please try..."

Closing - Positive & Forward-Looking:
"We're constantly improving [app] based on feedback like yours..."

Common Issue Categories:

  1. Technical: Crashes, bugs, performance
  2. Account: Login, password, subscription
  3. Feature: How-to, confusion, requests
  4. Billing: Payments, refunds, upgrades
  5. Content: Inappropriate, missing, quality
  6. Integration: Third-party connections

Escalation Decision Tree:

  • Angry user + technical issue → Developer immediate
  • Payment problem → Finance team + apologetic response
  • Feature confusion → Create documentation + product feedback
  • Repeated issue → Automated response + tracking
  • Press/Influencer → Marketing team + priority handling

Read the full file on GitHub · 162 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. yesterday First seen · 162 lines · 45 tokens per session scan A 9717512a45b2

Subscribe to this mod's changes

support-responder is an agent published in the GitHub repository PMDevSolutions/Aurelius (8 stars, last pushed 21d ago), licensed MIT. It adds 45 tokens to every session and 1,335 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 2026-09-04.

Related

Other agents, from other repositories

chief-of-staff

Personal communication chief of staff that triages email, Slack, LINE, and Messenger. Classifies messages into 4 tiers (skip/infoonly/meetinginfo/actionrequired), generates draft replies, and enforces post-send follow-through via hooks. Use when managing multi-channel communication workflows.

Yaomeng1749/claude-code-digital-nomad-config-pack · 61 tokens

software-architect

Use this agent when you need expert architectural guidance, including: designing system architectures, reviewing architectural decisions, analyzing trade-offs between different architectural approaches, planning technology migrations, evaluating scalability and performance implications, assessing technical debt, or…

patrickserrano/lacquer · 0 tokens

concurrency-reviewer

Concurrency & race-condition reviewer. Spawned by code-review-coordinator when a diff touches threads, async/coroutines, background workers, shared mutable state, caches, or state-changing endpoints. Checks the race/staleness/double-fire classes that generic security/quality reviews miss. Created after a…

shashankreddy509/claude-tdd-kit · 80 tokens

healthcare-reviewer

Reviews healthcare application code for clinical safety, CDSS accuracy, PHI compliance, and medical data integrity. Specialized for EMR/EHR, clinical decision support, and health information systems.

Yaomeng1749/claude-code-digital-nomad-config-pack · 42 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens