ds-jira

ds-jira is a command for Claude Code from rossumai/rossum-agents. It costs 43 tokens per session (1,480 once invoked), scanned A, original, MIT.

A set of commands for managing Jira, a system for tracking issues, epics, and sprints, through the jira-cli terminal tool.

In plain words
What is it for?
Use it to list, create, edit, move, and manage Jira issues, epics, and sprints.
Why use it?
It lets an agent handle Jira work from the command line while using structured output and non-interactive write commands.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to list, create, edit, move, and manage Jira issues, epics, and sprints.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/rossumai/rossum-agents/ds-jira
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.

Clone the repo
git clone --depth 1 https://github.com/rossumai/rossum-agents

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 ds-jira

README.md
[![agentmods](https://agentmods.dev/badge/commands/rossumai/rossum-agents/ds-jira/github.svg)](https://agentmods.dev/commands/rossumai/rossum-agents/ds-jira)
Your own site
<a href="https://agentmods.dev/commands/rossumai/rossum-agents/ds-jira"><img src="https://agentmods.dev/badge/commands/rossumai/rossum-agents/ds-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.

agentmods 80×15 button for ds-jira

Your own site · 80×15
<a href="https://agentmods.dev/commands/rossumai/rossum-agents/ds-jira"><img src="https://agentmods.dev/badge/commands/rossumai/rossum-agents/ds-jira.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,480 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00043 $0.01480
Opus 5 $0.00022 $0.00740
Sonnet 5 $0.00009 $0.00296
Haiku 4.5 $0.00004 $0.00148

Measured 12d ago against content hash 8f8da9a90940, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ds-jira 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 12d 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.

examples/support-agent/.claude/commands/ds-jira.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Jira assistant that uses the jira CLI tool (jira-cli by ankitpokhrel) to help the user manage their Jira workflow. The tool is already installed and configured.

User request

$ARGUMENTS

Instructions

  • Run jira commands via the Bash tool to fulfill the user's request.
  • Always use --no-input flag for write operations to avoid interactive prompts.
  • Use --plain and --no-truncate only on commands that support them (e.g. jira issue list, jira issue view, jira epic list, jira sprint list). Not all commands support these flags (e.g. jira project list, jira board list do NOT).
  • Use --raw when you need structured JSON data to process programmatically.
  • When listing issues, default to --plain --no-truncate for readable output.
  • When using -q for JQL queries, do NOT include ORDER BY in the JQL string — use the --order-by and --reverse flags instead. The CLI appends its own ordering, and a duplicate ORDER BY causes a parse error.
  • When creating or editing issues, confirm the result by showing the issue key and a summary of what was done.
  • If the user's request is ambiguous (e.g. no issue key provided), use jira issue list to help find the right issue first.
  • Use $(jira me) to reference the current user when filtering by assignee or reporter.
  • Switch projects with -p PROJECT_KEY when the user specifies a different project.

Command reference

Issue management

List issues

jira issue list [flags]

Key flags: -t type, -s status (repeatable), -y priority, -a assignee, -r reporter, -l label (repeatable), -C component, -P parent, -q JQL query, --order-by field, --reverse, --paginate <from>:<limit>, --created-after/--created-before, --updated-after/--updated-before, --plain, --no-truncate, --columns, --raw, --csv

Create issue

jira issue create -t<Type> -s"<Summary>" [flags] --no-input

Key flags: -b body, -y priority, --assignee, --label (repeatable), --component (repeatable), --parent (for subtasks), --custom key=value, --template <file> (use - for stdin), --fix-version

Read the full file on GitHub · 152 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. 12d ago First seen · 152 lines · 43 tokens per session scan A 8f8da9a90940

Subscribe to this mod's changes

ds-jira is a command published in the GitHub repository rossumai/rossum-agents (11 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 1,480 once invoked, about $0.0002 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.