jira-assistant

jira-assistant is a skill for Claude Code from grandcamel/JIRA-Assistant-Skills. It costs 37 tokens per session (2,442 once invoked), scanned A, original, MIT.

A JIRA routing hub that directs requests to one of 13 specialized skills for issues, workflows, Agile planning, search, time tracking, service management, and related tasks. JIRA is a system for tracking project work and support requests.

In plain words
What is it for?
Use it to route requests involving issues, JQL searches, status changes, epics, sprints, comments, dependencies, worklogs, service desks, and bulk operations.
Why use it?
It helps identify the appropriate JIRA workflow instead of choosing among many specialized operations manually.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the jira-assistant-skills plugin — 14 skills, 4 commands, 15 agents shipped together

Good fit Use it to route requests involving issues, JQL searches, status changes, epics, sprints, comments, dependencies, worklogs, service desks, and bulk operations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/grandcamel/jira-assistant-skills/jira-assistant
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.

Any agent
npx skills add grandcamel/JIRA-Assistant-Skills --skill jira-assistant
Clone the repo
git clone --depth 1 https://github.com/grandcamel/JIRA-Assistant-Skills

Made for: Claude Code.

Or install jira-assistant-skills, the plugin that ships this one along with the rest of its 14 skills, 4 commands, 15 agents.

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-assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/grandcamel/jira-assistant-skills/jira-assistant/github.svg)](https://agentmods.dev/skills/grandcamel/jira-assistant-skills/jira-assistant)
Your own site
<a href="https://agentmods.dev/skills/grandcamel/jira-assistant-skills/jira-assistant"><img src="https://agentmods.dev/badge/skills/grandcamel/jira-assistant-skills/jira-assistant/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 jira-assistant

Your own site · 80×15
<a href="https://agentmods.dev/skills/grandcamel/jira-assistant-skills/jira-assistant"><img src="https://agentmods.dev/badge/skills/grandcamel/jira-assistant-skills/jira-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,442 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

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 →

  • high Anti-Refusal · line 235
    Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
    Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
  • medium Excessive Agency · line 234
    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.
How audits are shown
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 $0.00037 $0.02442
Opus 5 $0.00018 $0.01221
Sonnet 5 $0.00007 $0.00488
Haiku 4.5 $0.00004 $0.00244

Measured 12d ago against content hash 6cb85fda5795, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

jira-assistant 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.

The scan reads SKILL.md. This mod also ships 24 executable files (tests/build-enhanced.sh, tests/claude_analyzer.py, tests/claude-devcontainer/config/setup-enhanced.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/jira-assistant/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JIRA Assistant

This hub routes requests to specialized JIRA skills. It does not execute JIRA operations directly—it helps find the right skill.

Risk Levels

Operation Risk Notes
Route to skill - Read-only routing decision
Skill discovery - Lists available skills
Context tracking - In-memory only

Risk Legend: - Safe, read-only | ! Caution, modifiable | !! Warning, destructive but recoverable | !!! Danger, irreversible

Quick Reference

I want to... Use this skill Risk
Create/edit/delete a single issue, view/show issue details jira-issue ⚠️
Search with JQL, export results jira-search -
Change status, assign, resolve, manage versions/components jira-lifecycle ⚠️
Manage sprints, epics, subtasks, story points jira-agile -
Add comments, attachments, watchers jira-collaborate -
Link issues, view dependencies, blocker chains jira-relationships -
Log time, manage worklogs, time reports jira-time -
Handle service desk requests, SLAs, queues, approvals, assets, knowledge base jira-jsm -
Bulk operations on many issues (50+) with dry-run preview jira-bulk ⚠️⚠️
Git branch names, commits, PR descriptions jira-dev -
Custom field discovery and Agile field configuration jira-fields -
Project discovery, cache management, diagnostics jira-ops -
Project settings, permissions, automation rules jira-admin ⚠️⚠️

Risk Legend: - Read-only/safe | ⚠️ Has destructive ops (confirm) | ⚠️⚠️ High-risk (confirm + dry-run)


Routing Rules

  1. Explicit skill mention wins - If user says "use jira-agile", use it
  2. Entity signals - Issue key present → likely jira-issue or jira-lifecycle
  3. Quantity determines bulk - 50+ issues → jira-bulk (consider bulk for 10+, required for 50+)
  4. Keywords drive routing:
    • "show", "view", "display", "get", "retrieve", "see", "details", "look up", "check" (with issue reference) → jira-issue
    • "create", "update", "delete" (single issue) → jira-issue
    • "search", "find", "JQL", "filter" → jira-search
    • "sprint", "epic", "backlog", "story points", "subtask" → jira-agile
    • "transition", "move to", "assign", "close", "version", "release", "component", "resolve", "reopen", "archive" → jira-lifecycle
    • "comment", "attach", "watch", "notify", "notification", "activity", "history", "changelog" → jira-collaborate
    • "link", "blocks", "depends on", "clone", "dependency graph", "blocker chain" → jira-relationships
    • "log time", "worklog", "estimate", "time report", "timesheet" → jira-time
    • "service desk", "SLA", "customer", "request", "queue", "approval", "knowledge base", "asset" → jira-jsm
    • "branch name", "commit", "PR" → jira-dev
    • "custom field", "field ID" → jira-fields
    • "cache", "warm cache", "project discovery", "diagnostics", "performance", "request batching" → jira-ops
    • "permissions", "project settings", "automation", "automation rule", "users", "groups", "notifications", "screens", "issue types", "workflows", "notification scheme", "permission scheme" → jira-admin

Read the full file on GitHub · 236 lines

Files

What ships with it

60 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.

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 · 236 lines · 37 tokens per session scan A 6cb85fda5795

Subscribe to this mod's changes

jira-assistant is a skill published in the GitHub repository grandcamel/JIRA-Assistant-Skills (46 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 2,442 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.

Related

Other skills, from other repositories