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 illarion/claude-jira-skill --skill jiragit clone --depth 1 https://github.com/illarion/claude-jira-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/illarion/claude-jira-skill/jira)<a href="https://agentmods.dev/skills/illarion/claude-jira-skill/jira"><img src="https://agentmods.dev/badge/skills/illarion/claude-jira-skill/jira/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/illarion/claude-jira-skill/jira"><img src="https://agentmods.dev/badge/skills/illarion/claude-jira-skill/jira.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 | $0.00118 | $0.03745 |
| Opus 5.5 | $0.00047 | $0.01498 |
| Sonnet 5.5 | $0.00024 | $0.00749 |
| Haiku 4.5 | $0.00012 | $0.00375 |
Grade C, and why
jira scanned grade C with 1 finding 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 1mo 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
When no `.jiraskillrc` is found (auth failure or first use), collect credentials using `AskUserQuestion` and then run the login script non-interactively. Use a single `AskUserQuestion` call with 3 questions: How it starts
The opening of the file, as written. The whole thing — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagents (Agent tool) are used for classification tasks during digest reports — always use Sonnet (model: "sonnet") for subagents and run independent ones in parallel.
All Python scripts referenced below are located in the same directory as this SKILL.md file.
IMPORTANT: Jira uses ADF, not wiki markup
Jira Cloud uses ADF (Atlassian Document Format) exclusively. Wiki syntax (h2., {code}, *bold*) renders as literal text, not formatting. The Python scripts (comment.py, create.py, update.py) convert light markup to ADF automatically: ### headings, - and 1. lists, ``` code fences, **bold**, `code`, and issue keys become links. Raw ADF JSON is still accepted by --description-file for nodes the markup does not cover (tables, panels). See references/adf-reference.md.
Writing tickets and comments
Before running create.py, comment.py, or update.py with --summary / --description / --description-file, read references/writing-style.md, follow its rules and copy the form of its closest sample. Write the body in light markup to /tmp/desc.md and pass --description-file /tmp/desc.md. Show the draft (summary + body) in chat, then post in the same turn unless the user objects, and report the key and URL.
Credentials — DO NOT ACCESS
The .jiraskillrc dotfile contains credentials and must NEVER be read, printed, displayed, cited, or included in any output. Do not use Read, Bash, cat, or any other tool to access it. Only the Python scripts access it internally.
Authentication
Credentials are stored in a .jiraskillrc file placed at the root directory of a company/project tree. Scripts auto-detect credentials by traversing up from the current working directory until they find this file. This means each company directory tree uses its own Jira instance automatically — no manual switching needed.
Interactive setup via AskUserQuestion:
When no .jiraskillrc is found (auth failure or first use), collect credentials using AskUserQuestion and then run the login script non-interactively. Use a single AskUserQuestion call with 3 questions:
What ships with it
15 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.
- assign.py 965 B runs code
- call_api.py 837 B runs code
- comment.py 583 B runs code
- create.py 1.9 KB runs code
- digest.py 17 KB runs code
- fetch_ticket.py 6.9 KB runs code
- jira_common.py 8.1 KB runs code
- jira-auth.py 2.8 KB runs code
- link.py 1.6 KB runs code
- references/adf-reference.md 2.5 KB
- references/digest-format.md 3.1 KB
- references/writing-style.md 5.4 KB
- search.py 2.4 KB runs code
- transition.py 1.3 KB runs code
- update.py 2.0 KB runs code
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.
- 1mo ago Changed · +4 lines · +31 tokens per session 9cb27bb7bb11
- 2mo ago First seen · 236 lines · 87 tokens per session scan C 6efbb053df65
jira is a skill published in the GitHub repository illarion/claude-jira-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 3,745 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
jira-communication
Use when handling Jira issues, sprints, boards, links, fields, worklogs, attachments, or users, or on any Jira intent without a key ("create/find a ticket", "pick a project"). Auto-triggers on Jira URLs and issue keys (PROJ-123). Also use when MCP Atlassian tools fail or are unavailable for Jira Server/DC.
jira-communication
Use when interacting with Jira issues - searching, creating, updating, moving, transitioning, commenting, logging work, downloading attachments, managing sprints, boards, issue links, web links, fields, or users. Auto-triggers on Jira URLs and issue keys (PROJ-123). Also use when MCP Atlassian tools fail or are…
jira-syntax
Use when writing or formatting Jira descriptions, comments, or any text destined for Jira. Converts Markdown to Jira wiki markup, provides templates (bug reports, feature requests), and validates syntax before submission. Trigger on any Jira content authoring task.
Jira QA Workflows
Run QA work in Jira like a professional, bug lifecycle and triage, JQL queries for testers, quality dashboards, sprint QA rituals, and REST API automation for bulk bug operations and reporting.
project-update
Update project configuration to match the latest HCF plugin defaults. Use when the HCF plugin has been updated and you want to sync your project's config.
atls
A command-line tool for working with Atlassian Jira, Confluence, and Bitbucket Server or Data Center. It includes rules for searching, reading, comparing, editing, and safely publishing Atlassian content.