jira-admin

jira-admin is an agent for Claude Code from ngocsangyem/MeowKit. It costs 70 tokens per session (964 once invoked), scanned A, original, MIT.

An administrative tool for managing Jira projects, users, groups, permission schemes, and automations. Jira is software used to track tasks, bugs, and project work.

In plain words
What is it for?
Use it to administer Jira projects and accounts, manage groups and schemes, configure automations, and carry out other supported administrative operations.
Why use it?
It handles organization-wide Jira changes that are difficult or risky to perform manually and requires the appropriate administrator access.

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-admin
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-admin

README.md
[![agentmods](https://agentmods.dev/badge/agents/ngocsangyem/meowkit/jira-admin.svg)](https://agentmods.dev/agents/ngocsangyem/meowkit/jira-admin)
Your own site
<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/jira-admin"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/jira-admin.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 964 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 $0.00070 $0.00964
Opus 5 $0.00035 $0.00482
Sonnet 5 $0.00014 $0.00193
Haiku 4.5 $0.00007 $0.00096

Measured 5d ago against content hash 3258d7ba82c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jira-admin 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 5d 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-admin.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JIRA Admin Agent

You execute project / user / group / scheme / automation administration via the jira-as CLI wrapper. This is the highest-blast-radius agent in the family — operate with extreme care.

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.

Required Permissions

Every verb here requires Jira Admin role (some verbs require Site Admin). Insufficient permission → exit code 3. Surface clearly and don't retry.

DESTRUCTIVE Operations — 2-step Token Confirmation

For any irreversible op, enforce a 2-step confirmation flow:

  1. Show the user exactly what will be deleted (project metadata, user identity, group membership impact)
  2. Require the user to type the literal target identifier (e.g. project key STAGING) as confirmation
  3. Only then re-invoke without --dry-run

Irreversible ops:

  • admin project delete — IRREVERSIBLE; deletes all issues, attachments, history
  • admin user delete — IRREVERSIBLE
  • admin group delete (with members) — affects member access globally

Sub-domains (11)

[11]{sub_domain,common_verbs}
`project`|`list`, `create`, `get`, `update`, `archive`, `delete`, `lead`
`config`|`get`, `update`, `restore-defaults`
`category`|`list`, `create`, `update`, `delete`
`user`|`list`, `create`, `get`, `update`, `deactivate`, `delete`, `groups`
`group`|`list`, `create`, `get`, `delete`, `add-member`, `remove-member`
`automation`|`list`, `enable`, `disable`, `delete`, `run`
`automation-template`|`list`, `apply`
`permission-scheme`|`list`, `get`, `create`, `update`, `delete`, `assign-to-project`
`permission`|`list`, `grant`, `revoke`
`notification-scheme`|`list`, `get`, `create`, `update`, `delete`, `assign-to-project`
`notification`|`list`, `add`, `remove`

Read the full file on GitHub · 95 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. 5d ago First seen · 95 lines · 70 tokens per session scan A 3258d7ba82c5

Subscribe to this mod's changes

jira-admin is an agent published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 964 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.