Borrowing it
Nothing to install: this file belongs to Dynokostya/just-works. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Dynokostya/just-works/main/.claude/skills/ticket-writing/SKILL.mdgit 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/skills/dynokostya/just-works/ticket-writing)<a href="https://agentmods.dev/skills/dynokostya/just-works/ticket-writing"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/ticket-writing/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/dynokostya/just-works/ticket-writing"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/ticket-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 24 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00078 | $0.04325 |
| Opus 5.5 | $0.00031 | $0.01730 |
| Sonnet 5.5 | $0.00016 | $0.00865 |
| Haiku 4.5 | $0.00008 | $0.00432 |
Grade A, and why
ticket-writing 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 17d 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ticket Writing
Match the project's existing conventions. When uncertain, read 3–5 recent tickets to infer local style — title form, section names, typical length, and link usage. These defaults apply only when the project has no established convention.
Never rules
These are unconditional. They prevent ambiguity, lost provenance, and wasted triage regardless of project style.
- Never ship a ticket whose title doesn't identify what will change. Titles like "bug" or "update" force every reader to open the ticket to find out. Titles are scanned in lists and boards far more often than they're clicked.
- Never omit Steps to reproduce on a Bug. Without numbered, specific steps, the dev re-derives the repro path from scratch — the single biggest cause of "cannot reproduce" churn.
- Never omit Expected and Actual results on a Bug. "It's broken" is not a specification. Expected is the target to fix toward; Actual is what was observed.
- Never write acceptance criteria using subjective terms — "fast", "intuitive", "user-friendly", "good UX". They're untestable. Quantify ("search returns under 500 ms at p95") or describe observable behavior.
- Never prescribe the solution inside the story body. "As a user, I want a React dropdown with debounced autocomplete..." locks the team into an implementation. Describe what the user needs; leave how to the implementer.
- Never mix multiple user roles in one story. "As a user and admin, I want..." is two stories. Split them — different permissions, different flows, different tests.
- Never leave placeholders in a published ticket —
[TBD],[TODO],[paste link]. Get the value before creating, ask, or add a follow-up comment after creation. Placeholders that survive to closure signal a weak process. - Never title a ticket with a trailing period. Wastes characters in scan-width views and doesn't match imperative-mood form.
- Never block work on a dependency without linking the blocker. If ticket A can't start until B ships, use a blocked-by link so the board and dependency tooling can surface it.
- Never create a ticket without checking that a similar one isn't already open. Duplicates fragment discussion, split assignment, and waste triage. Search the target tracker by title keywords and by likely tags first. Surface near-matches to the requester and let them decide: dedupe, link as relates-to, or proceed.
- Never include a section, field, or value the user didn't request or you haven't confirmed. Required values for the type get asked, not guessed (Bug's Severity in the body; Spike's timebox and Bug's priority in native fields). Optional sections stay omitted unless the user supplies the content (Open questions, Attachments, Links). Inventing values to match a template pollutes the ticket with content the user must re-check, and erodes trust that the body reflects their intent.
What ships with it
1 file 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.
- 17d ago Changed · -25 lines 0083540db726
- 1mo ago Changed · -24 lines 39d41fb78d9d
- 2mo ago First seen · 330 lines · 78 tokens per session scan A d9e210127223
ticket-writing is a skill published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 78 tokens to every session and 4,325 once invoked, about $0.0003 per session on Opus 5.5. 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.
ticket-writing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ticket-writingDynokostya/just-works | Skill | 14 | 10d ago | Apache-2.0 | A | 78 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |