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 skills add adonai-labs/agent-runway --skill ticket-creatorgit clone --depth 1 https://github.com/adonai-labs/agent-runwayWrote 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/adonai-labs/agent-runway/ticket-creator)<a href="https://agentmods.dev/skills/adonai-labs/agent-runway/ticket-creator"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/ticket-creator/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.
<a href="https://agentmods.dev/skills/adonai-labs/agent-runway/ticket-creator"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/ticket-creator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00061 | $0.05283 |
| Opus 5 | $0.00030 | $0.02642 |
| Sonnet 5 | $0.00012 | $0.01057 |
| Haiku 4.5 | $0.00006 | $0.00528 |
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 10d 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 — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ticket Creator
Creates development-ready tickets by combining Product Owner and Business Analyst perspectives. Takes a brief input and produces a structured, validated ticket.
When to Use
- Creating a new ticket from a brief description
- Refining an existing Jira ticket or markdown requirement
- Preparing backlog items for development
- User says "create ticket", "write user story", "prepare requirement", "refine ticket"
Supported Task Types
| Type | Description |
|---|---|
| Feature | New functionality or enhancement to existing behaviour |
| Bug | Defect in existing functionality |
| Task | Technical or operational work with no direct user-facing outcome (e.g. configuration change, dependency upgrade, refactor, infrastructure change) |
Core Principles
Apply shared policy: ../shared/caveman-skill-engineering.md
- Start with a complete draft, refine from there — no lengthy upfront questions
- Uses your project documentation automatically — when available, docs enrich the ticket silently
- Covers the business case and the developer details — both the "why" and the "how" in one ticket
- Checks the ticket is dev-ready before asking you to approve — gaps are flagged early
- Works on any project — adapts to your docs and codebase automatically
- Simple to use, technical when needed — conversation stays in plain language; the ticket output is as detailed and technical as a developer needs
- Clarity over exhaustiveness — a ticket that is easy to read and act on is better than one that is complete but overwhelming; leave out detail that does not help a developer start work
- A ticket is not a spec — if a section is expanding into a design document, stop; capture the essential requirement and move the detail elsewhere
- Extensive detail belongs in subtasks or separate tickets — if implementation steps, edge cases, or technical notes become lengthy, extract them into linked follow-up tickets rather than bloating the parent
- Suggest a split when complexity is high — if the ticket spans multiple independent user-facing outcomes, requires work across more than two distinct system layers with no shared delivery milestone, or produces acceptance criteria that would reasonably take more than one sprint to verify, flag it and offer to split it before proceeding
- Prefer atomic implementation units — ticket guidance should push decomposition into small single-purpose functions/modules, not one large multi-responsibility function
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 481 lines · 61 tokens per session scan A 69634a486991
ticket-creator is a skill published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 20d ago), licensed MIT. It adds 61 tokens to every session and 5,283 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
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
gentle-ai-bench
Trigger: bench, journey, journeys, driven mode, gentle-ai-bench, journey corpus, j-numbers, bench axis. Author and verify gentle-ai bench journeys; go test ./bench never proves driven execution.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.