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 kirti/jira-ticket-builder-skill --skill skillgit clone --depth 1 https://github.com/kirti/jira-ticket-builder-skillWrote 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/kirti/jira-ticket-builder-skill/skill)<a href="https://agentmods.dev/skills/kirti/jira-ticket-builder-skill/skill"><img src="https://agentmods.dev/badge/skills/kirti/jira-ticket-builder-skill/skill/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/kirti/jira-ticket-builder-skill/skill"><img src="https://agentmods.dev/badge/skills/kirti/jira-ticket-builder-skill/skill.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 | $0.00213 | $0.04000 |
| Opus 5.5 | $0.00085 | $0.01600 |
| Sonnet 5.5 | $0.00043 | $0.00800 |
| Haiku 4.5 | $0.00021 | $0.00400 |
Grade A, and why
jira-ticket-builder 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 21d 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 — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jira Ticket Builder
Converts rough input into a structured, ready-to-paste Jira ticket. Built around the pipeline:
ROUGH INPUT → Understand Input → Extract Facts → Fill Missing Data / Ask →
Generate Ticket → Validate → Jira Ticket
Step 0 — Single ticket vs. decomposition
Before running the single-ticket pipeline below, check the input's shape:
- Single ticket: one bug, one feature ask, one clear unit of work → proceed with Steps 1-5 as below.
- Decomposition: a rough requirements document — meeting notes, a product brief, an email thread, a spec with multiple asks and open questions bundled together — where a single ticket would be too large or would hide independently-shippable pieces → use Decomposition Mode below instead of Steps 1-5.
Signal for decomposition mode: multiple distinct capabilities mentioned, a "Questions:" section, or the user says things like "break this down," "turn this into stories," or pastes a document rather than a single ask.
Decomposition Mode
For a rough requirements document that needs to become multiple linked Jira stories with full traceability and an explorable dashboard.
D1 — Analyze the document
Read the whole document first. Extract, without inventing:
- Business context — objectives, actors (who's involved), business rules, and the business
flow (actor → action → system, as an ordered sequence if the doc describes a process). Where a
step has a UI screen or a callable API/system, note it (
ui_screen/api) — this is what lets the Customer Journey diagram show the full stack per step, not just the business narrative. - Business requirements — the business objective/problem/value being addressed
- Functional requirements — what the system must do
- Non-functional requirements — performance, security, accessibility, compliance
- Ambiguities — anything incomplete, contradictory, vague, or missing acceptance criteria/technical decisions
Mark every requirement, objective, and business rule confidence: "confirmed" (stated in the
doc) or "inferred" (you concluded it from context) — never leave this implicit.
What ships with it
10 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.
- assets/build_portal.py 8.0 KB runs code
- assets/decomposition.schema.json 18 KB
- assets/export_jira.py 12 KB runs code
- assets/full-template.md 5.4 KB
- assets/portal-page-template.html 51 KB
- assets/quality_gate.py 16 KB runs code
- assets/quick-template.md 710 B
- assets/story-template.md 5.6 KB
- references/decomposition-schema.md 9.3 KB
- references/section-guide.md 3.2 KB
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.
- 21d ago Changed · +2 lines 4959d424ee5e
- 1mo ago First seen · 285 lines · 213 tokens per session scan A 757a926d60f1
jira-ticket-builder is a skill published in the GitHub repository kirti/jira-ticket-builder-skill (2 stars, last pushed 21d ago), licensed MIT. It adds 213 tokens to every session and 4,000 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
nx-workspace
Nx workspace rules: running targets, affected commands, generators, project.json and the Nx MCP tools. Use when running or generating anything in an Nx monorepo, editing project.json, or reading its dependency graph.
trello-task-management
Trello cards, checklists and boards for kanban tracking. Use when creating or moving Trello cards, adding checklists, or tracking work on a Trello board.
jira-management
Jira issues, epics, sprints, backlog and workflow transitions. Use when creating or updating Jira issues, linking epics, moving work through a sprint, or searching the backlog.
linear-task-management
Linear issue conventions: naming, labels, priorities, status transitions and PR links. Use when creating or updating Linear issues, breaking a feature into Linear tasks, or resuming work tracked in Linear.
spec-to-backlog
Automatically convert Confluence specification documents into structured Jira backlogs with Epics and implementation tickets. When an agent needs to: (1) Create Jira tickets from a Confluence page, (2) Generate a backlog from a specification, (3) Break down a spec into implementation tasks, or (4) Convert requirements…
triage-issue
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…