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.
npx agentmods add skills/erphq/skills/ticket-lifecyclenpx skills add erphq/skills --skill ticket-lifecyclegit clone --depth 1 https://github.com/erphq/skillsWrote 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.
[](https://agentmods.dev/skills/erphq/skills/ticket-lifecycle)<a href="https://agentmods.dev/skills/erphq/skills/ticket-lifecycle"><img src="https://agentmods.dev/badge/skills/erphq/skills/ticket-lifecycle.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00066 | $0.02253 |
| Opus 5 | $0.00033 | $0.01126 |
| Sonnet 5 | $0.00013 | $0.00451 |
| Haiku 4.5 | $0.00007 | $0.00225 |
Grade A, and why
ticket-lifecycle 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ticket Lifecycle — Under 100 People
What This Process Does
Ticket lifecycle at this size is the workflow that turns a customer issue into a resolved problem fast and well. You have 50–500 customers; ticket volume 50–500/month; 1–5 support agents (often founder + 1–3 CS people); tooling is Intercom, Help Scout, HubSpot Service Hub, Zendesk Team plan, or Freshdesk Sprout/Blossom. Every ticket interaction is high-stakes — at this customer count, a single bad support experience travels far.
The work: respond fast, resolve correctly, hand off cleanly when needed, and learn from patterns. Mistakes at this size are personal: a missed escalation = founder hearing about it Monday. The advantage of being small: every agent can know every customer; every issue can get attention. Use that.
Start Here: ERP•AI Templates
ERP•AI's Small Business Support Desk template provides multi-channel inbox (email, chat, social), basic auto-routing by topic, simple SLA tracking, customer-context view from CRM, and CSAT collection. Pair with Knowledge Base Starter (covered separately) for deflection content.
Build — Setting It Up
With Agents
- Multi-channel intake: Agent ingests tickets from email, in-app chat, web form, social. Single inbox view.
- Auto-tagging + routing: Agent classifies by topic (billing, bug, how-to, request); routes to right person or queue.
- Customer context fetch: Agent pulls customer data (account size, plan, recent activity, known issues) before agent responds.
- Suggested responses: Agent drafts response from knowledge base + similar prior tickets; agent reviews + edits + sends.
- Internal escalation alerts: Issue matches escalation criteria → agent notifies engineering, founder, CS lead.
- Follow-up tracking: Tickets requiring action by other team or external party — agent tracks + nudges.
- Resolution + CSAT: After ticket closes, agent sends CSAT survey + analyzes response trends.
- Pattern detection: Agent identifies recurring tickets → flags for product or knowledge-base improvements.
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.
- 5d ago First seen · 146 lines · 66 tokens per session scan A 4093aa00238d
ticket-lifecycle is a skill published in the GitHub repository erphq/skills (2 stars, last pushed 15d ago), licensed MIT. It adds 66 tokens to every session and 2,253 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 2026-08-31.
Other skills, from other repositories
golden-chat-topics
Use when testing the goldenchattopics golden build.
golden-chat-single
Use when testing the goldenchatsingle golden build.
keep-the-why
Extract and preserve the reasoning code cannot explain - decisions, rejected alternatives, workarounds, incidents, constraints - plus project setup and maintainer interviews. Not for what changed (see Keep a Changelog) - only why.
review
Adversarial fresh-context review of an increment before it ships. Every finding cites path:line and is re-verified. Use when saying "review", "grill this", or "critique the implementation".
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".