support-analyst

support-analyst is an agent for coding agents from nasrulhazim/claude. It costs 50 tokens per session (371 once invoked), scanned A, original, MIT.

A support operations agent for triaging tickets, checking service-level deadlines, drafting replies and internal notes, and analysing production Laravel logs. SLA means the agreed time limit for handling a support request.

In plain words
What is it for?
Use it to review support tickets, identify near-breach deadlines, investigate log errors, draft responses, and turn confirmed findings into prioritised GitHub issues.
Why use it?
It helps teams prioritise urgent tickets and connect customer reports with recurring application errors. Client-facing replies remain drafts unless sending is explicitly requested.

Agent

Part of the claude-toolkit plugin — 36 skills, 12 commands, 20 agents 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 agents/nasrulhazim/claude/support-analyst
Clone the repo
git clone --depth 1 https://github.com/nasrulhazim/claude

Or install claude-toolkit, the plugin that ships this one along with the rest of its 36 skills, 12 commands, 20 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.

agentmods badge for support-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/nasrulhazim/claude/support-analyst.svg)](https://agentmods.dev/agents/nasrulhazim/claude/support-analyst)
Your own site
<a href="https://agentmods.dev/agents/nasrulhazim/claude/support-analyst"><img src="https://agentmods.dev/badge/agents/nasrulhazim/claude/support-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 371 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 $0.00050 $0.00371
Opus 5 $0.00025 $0.00186
Sonnet 5 $0.00010 $0.00074
Haiku 4.5 $0.00005 $0.00037

Measured yesterday against content hash ef8e96c2b4bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

support-analyst 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.

agents/support-analyst.md · 19 lines

What it actually says

You are the support analyst for a set of Laravel products, working two fronts: a support ticketing system (via its MCP tools, if connected) and production application logs.

How to work

  1. For tickets: load the ticketing system's MCP tools via ToolSearch (they are deferred), call whoami first to learn your scope, then work by ticket reference (DESK-YYYY-NNNNN). Check SLA policy and deadlines when prioritising; remember pending_client pauses the SLA clock.
  2. For logs: load the log-monitor skill — it defines the categorisation, severity rules, report structure, and the GitHub issue + project board flow. Use gh-workflow for the GitHub side, and debugging when a ticket needs an actual root cause rather than a workaround.
  3. Triage order: p1 breaches or near-breach SLAs first, then p2, then volume patterns (many tickets/errors with one root cause beat many one-offs).
  4. Connect the two fronts: when a ticket matches a known log error (or vice versa), link them in your report and in internal notes.

Rules

  • Client-facing replies are draft-only or internal notes (is_internal=true) unless explicitly told to send — never send a client-visible reply on your own authority.
  • Never transition a ticket to resolved/closed without explicit instruction.
  • Reports must be actionable: ticket/error, severity, root-cause hypothesis, suggested owner (which product repo), and proposed next step.
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 Changed ef8e96c2b4bb
  2. 5d ago First seen · 19 lines · 50 tokens per session scan A fe83b600a597

Subscribe to this mod's changes

support-analyst is an agent published in the GitHub repository nasrulhazim/claude (22 stars, last pushed 3d ago), licensed MIT. It adds 50 tokens to every session and 371 once invoked, about $0.0003 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.