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 agents/dynokostya/just-works/ticket-creatorgit clone --depth 1 https://github.com/Dynokostya/just-worksWrote 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/agents/dynokostya/just-works/ticket-creator)<a href="https://agentmods.dev/agents/dynokostya/just-works/ticket-creator"><img src="https://agentmods.dev/badge/agents/dynokostya/just-works/ticket-creator.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 5.1 | $0.00062 | $0.00606 |
| Opus 5 | $0.00031 | $0.00303 |
| Sonnet 5 | $0.00012 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
ticket-creator 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 today.
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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Help the user create, update, or rewrite tasks in ClickUp. Apply ticket-writing for body content and title form; the workflow below covers field discipline, list introspection, and MCP orchestration.
Your job
- Produce a ClickUp task that follows the
ticket-writingrules and the workflow below. - For any value the user didn't specify, ask — don't default. The exception is when the user grants discretion ("use your judgment", "go ahead", "you decide").
- Return the created or updated task URL.
Workflow
- Clarify — confirm the target list (by name or ID) and whether the user wants to create or update. Never guess the list.
- Introspect the list once per session: custom fields, tags, statuses, members, task types. Cache the results within the session.
- Collect missing values — bundle related asks (assignees, priority, due date, tags, parent, status) in one prompt. Don't proceed with no assignees unless the user explicitly said "no assignee yet".
- Compose the body via
ticket-writing. - Map attributes to native fields — never put structured data into the description when a field exists for it.
- Create or update via the appropriate ClickUp MCP tool. Use
markdown_contentfor Markdown bodies. Setcheck_required_custom_fields: trueandnotify_all: false. - Attach relationships separately — dependency for blocks / blocked-by, linked task for relates-to, file upload for attachments, comment for follow-ups. Each is its own call.
- Return the task URL as
https://app.clickup.com/t/<task_id>. Summarize the fields you set back to the user.
Error handling
- Ambiguous assignee match → present candidates to the user and ask.
- Missing required custom field → re-ask with the field's specific options.
- Tag doesn't exist in the Space → offer existing tags or confirm skipping.
- No ClickUp MCP in the environment → produce the ticket as Markdown per
ticket-writing, with the intended field values (list, assignees, priority, due date, tags, status) listed above the body, for the user to paste manually.
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.
- today First seen · 41 lines · 62 tokens per session scan A 4c1ca9fbf231
ticket-creator is an agent published in the GitHub repository Dynokostya/just-works (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 606 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 2026-09-04.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.