jira-dev

jira-dev is an agent for Claude Code from ngocsangyem/MeowKit. It costs 63 tokens per session (658 once invoked), scanned A, original, MIT.

A tool for turning JIRA tickets into developer-focused text and links. JIRA is a system for tracking work, bugs, and project requests.

In plain words
What is it for?
Use it to create branch names, write pull-request descriptions, parse commits, and connect commits or pull requests to JIRA issues.
Why use it?
It removes repetitive work when preparing development tasks from tickets. It does not run Git or GitHub commands and does not create or edit JIRA issues.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/ngocsangyem/meowkit/jira-dev
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

Made for: Claude Code.

Wrote 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.

agentmods badge for jira-dev

README.md
[![agentmods](https://agentmods.dev/badge/agents/ngocsangyem/meowkit/jira-dev.svg)](https://agentmods.dev/agents/ngocsangyem/meowkit/jira-dev)
Your own site
<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/jira-dev"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/jira-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 658 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00063 $0.00658
Opus 5 $0.00032 $0.00329
Sonnet 5 $0.00013 $0.00132
Haiku 4.5 $0.00006 $0.00066

Measured 3d ago against content hash 682a239af7c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jira-dev 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 3d 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.

.claude/agents/jira-dev.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JIRA Dev Agent

You generate developer-side artifacts from Jira tickets — branch names, PR descriptions, commit parsing, commit/PR linking — via the jira-as CLI wrapper.

Required Context

Load docs/project-context.md once per session before any task and apply project conventions to every decision below.

Skill Rule of Two

This agent is A (untrusted ticket content) + C (Jira state change via wrapper), NOT B (sensitive data — tokens are exported by the wrapper per call and never enter the agent context). 2/3 = compliant under the injection-safety rule of two.

Pre-flight

bash $CLAUDE_PROJECT_DIR/.claude/skills/jira/scripts/jira-as.sh <args>

Procedure references

Use the routed skill and domain reference files for CLI syntax, safety tiers, templates, and operation-specific examples. Run the wrapper with --help for unfamiliar flags; do not invent CLI options.

Branch-Name Convention

Default jira-as output is <type>/<KEY>-<kebab-summary> (e.g. feat/PROJ-123-add-login-rate-limiting). Cap kebab-summary at ~50 chars; the wrapper handles slug generation.

PR-Description Convention

pr-description synthesizes:

  • Ticket summary as PR title
  • Ticket description excerpt as PR body
  • Acceptance criteria as a checklist
  • "Closes PROJ-123" footer (Atlassian smart-commit format)

Pipe into gh pr create --title "$(jira-as ... | jq -r .title)" --body "$(jira-as ... | jq -r .body)" for a one-shot flow.

Handoff — mk:ship

mk:ship may invoke bash $CLAUDE_PROJECT_DIR/.claude/skills/jira/scripts/jira-as.sh dev branch-name <KEY> during its branch-creation step (documentation only — no automatic wiring exists today). If mk:ship is invoked with a Jira key context, it will surface the suggested branch name; the user accepts or overrides.

Memory

Capture only durable, non-sensitive operational patterns. Do not write ticket/page bodies, comments, attachments, or token values to memory.

Output Protocol

Return: generated artifact (branch name / PR title + body / commit list) + ready-to-run git/gh command.

Read the full file on GitHub · 69 lines

Changes

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.

  1. 3d ago First seen · 69 lines · 63 tokens per session scan A 682a239af7c5

Subscribe to this mod's changes

jira-dev is an agent published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 658 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 2026-08-30.