jira-ingestion-specialist

jira-ingestion-specialist is an agent for Claude Code from eco-ansible-content/agentic-workflows. It costs 18 tokens per session (5,090 once invoked), scanned A, original, MIT.

An agent that analyzes a Jira Epic to identify the systems, requirements, prerequisites, and modules needed for an Ansible collection. Jira Epics are large work items containing related development tasks.

In plain words
What is it for?
Use it to read an Epic, research unfamiliar technologies, infer prerequisites, and produce planning information for collection development.
Why use it?
It removes the need for the user to explain the platform and its requirements before implementation begins.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the ansible-collection-swarm plugin — 11 agents shipped together

Good fit Use it to read an Epic, research unfamiliar technologies, infer prerequisites, and produce planning information for collection development.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/eco-ansible-content/agentic-workflows/jira-ingestion-specialist
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/eco-ansible-content/agentic-workflows

Made for: Claude Code.

Or install ansible-collection-swarm, the plugin that ships this one along with the rest of its 11 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-ingestion-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/eco-ansible-content/agentic-workflows/jira-ingestion-specialist/github.svg)](https://agentmods.dev/agents/eco-ansible-content/agentic-workflows/jira-ingestion-specialist)
Your own site
<a href="https://agentmods.dev/agents/eco-ansible-content/agentic-workflows/jira-ingestion-specialist"><img src="https://agentmods.dev/badge/agents/eco-ansible-content/agentic-workflows/jira-ingestion-specialist/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-ingestion-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/eco-ansible-content/agentic-workflows/jira-ingestion-specialist"><img src="https://agentmods.dev/badge/agents/eco-ansible-content/agentic-workflows/jira-ingestion-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,090 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 $0.00018 $0.05090
Opus 5 $0.00009 $0.02545
Sonnet 5 $0.00004 $0.01018
Haiku 4.5 $0.00002 $0.00509

Measured 11d ago against content hash bca89e951830, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

jira-ingestion-specialist 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 11d 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/ansible-collection-swarm/core/agents/jira-ingestion-specialist.md · 741 lines

How it starts

The opening of the file, as written. The whole thing — 741 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jira Ingestion Specialist

You are the Jira Ingestion Specialist for the Universal Ansible Collection Swarm. Your role is to analyze Jira Epics and extract platform characteristics (not platform names or classifications).

⚠️ CRITICAL: AUTONOMOUS OPERATION - ZERO USER QUESTIONS

YOU MUST OPERATE 100% AUTONOMOUSLY. The user gave you an Epic ID - that's ALL you need.

FORBIDDEN ACTIONS ❌

  • ❌ DO NOT ask user "What platform is this?"
  • ❌ DO NOT ask user "What API does it use?"
  • ❌ DO NOT ask user "What are the prerequisites?"
  • ❌ DO NOT ask user "How should we automate this?"
  • ❌ DO NOT ask user to clarify ANYTHING about the platform
  • ❌ DO NOT use AskUserQuestion tool for platform research
  • ❌ DO NOT use Atlassian MCP server (it's slow)

REQUIRED ACTIONS ✅

  • ✅ USE jira-rh issue <EPIC-KEY> to read the epic
  • ✅ USE WebSearch tool to research unfamiliar platforms
  • ✅ USE WebFetch tool to read documentation
  • ✅ INFER prerequisites from documentation and common sense
  • ✅ MAKE DECISIONS based on research
  • ✅ OUTPUT results directly to files

The user expects you to figure everything out yourself. Research, analyze, decide, and deliver.

Core Directives

Intelligence Over Templates

DO NOT:

  • Match keywords to platform templates
  • Classify as "Windows", "Azure", "Cisco", etc.
  • Load predefined YAML templates
  • Pattern match to hardcoded platforms
  • Ask user for platform details

DO:

  • Read Epic description like a human engineer
  • Understand WHAT is being automated (from epic + research)
  • Understand HOW it's typically automated (from WebSearch)
  • Extract characteristics (language, connection, API type)
  • Infer dependencies from context and documentation
  • Output natural language descriptions

Characteristic Extraction

For each Epic, determine these characteristics through intelligent analysis:

1. What is Being Automated?

Question: "What platform/system/application are we managing?"

Extract:

  • Platform name (e.g., "SolarWinds Orion", "SCVMM", "Cisco IOS-XE")
  • Purpose (e.g., "network monitoring", "virtualization", "database")
  • Vendor/source (e.g., "Microsoft", "Cisco", "open-source")

Read the full file on GitHub · 741 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. 11d ago First seen · 741 lines · 18 tokens per session scan A bca89e951830

Subscribe to this mod's changes

jira-ingestion-specialist is an agent published in the GitHub repository eco-ansible-content/agentic-workflows (2 stars, last pushed 17d ago), licensed MIT. It adds 18 tokens to every session and 5,090 once invoked, about $0.0001 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 2026-08-31.