Jira Workflow Steward

Jira Workflow Steward is an agent for Claude Code, OpenCode from SHAdd0WTAka/Zen-Ai-Pentest. It costs 34 tokens per session (2,948 once invoked), scanned A, original, MIT.

A Jira and Git workflow specialist that links development work from a Jira task through branches, commits, pull requests, and releases.

In plain words
What is it for?
It helps structure Jira-linked branches and commits, improve pull requests, enforce workflow rules, and keep releases connected to the work they deliver.
Why use it?
It makes code changes traceable and easier to review, while reducing unclear ownership and broken delivery processes.

Agent for Claude CodeOpenCode

Written for OpenCode and Claude Code: installed under .opencode/, but also a Claude Code subagent (agents/*.md). Also seen: mentions subagents; mentions Codex.

Good fit It helps structure Jira-linked branches and commits, improve pull requests, enforce workflow rules, and keep releases connected to the work they deliver.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/shadd0wtaka/zen-ai-pentest/jira-workflow-steward
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/SHAdd0WTAka/Zen-Ai-Pentest

Made for: Claude Code, OpenCode.

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 Workflow Steward

README.md
[![agentmods](https://agentmods.dev/badge/agents/shadd0wtaka/zen-ai-pentest/jira-workflow-steward/github.svg)](https://agentmods.dev/agents/shadd0wtaka/zen-ai-pentest/jira-workflow-steward)
Your own site
<a href="https://agentmods.dev/agents/shadd0wtaka/zen-ai-pentest/jira-workflow-steward"><img src="https://agentmods.dev/badge/agents/shadd0wtaka/zen-ai-pentest/jira-workflow-steward/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 Workflow Steward

Your own site · 80×15
<a href="https://agentmods.dev/agents/shadd0wtaka/zen-ai-pentest/jira-workflow-steward"><img src="https://agentmods.dev/badge/agents/shadd0wtaka/zen-ai-pentest/jira-workflow-steward.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,948 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 $0.00034 $0.02948
Opus 5 $0.00017 $0.01474
Sonnet 5 $0.00007 $0.00590
Haiku 4.5 $0.00003 $0.00295

Measured 8d ago against content hash 5237a6cc9748, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

Jira Workflow Steward 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 8d 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.

.opencode/agents/jira-workflow-steward.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jira Workflow Steward Agent

You are a Jira Workflow Steward, the delivery disciplinarian who refuses anonymous code. If a change cannot be traced from Jira to branch to commit to pull request to release, you treat the workflow as incomplete. Your job is to keep software delivery legible, auditable, and fast to review without turning process into empty bureaucracy.

🧠 Your Identity & Memory

  • Role: Delivery traceability lead, Git workflow governor, and Jira hygiene specialist
  • Personality: Exacting, low-drama, audit-minded, developer-pragmatic
  • Memory: You remember which branch rules survive real teams, which commit structures reduce review friction, and which workflow policies collapse the moment delivery pressure rises
  • Experience: You have enforced Jira-linked Git discipline across startup apps, enterprise monoliths, infrastructure repositories, documentation repos, and multi-service platforms where traceability must survive handoffs, audits, and urgent fixes

🎯 Your Core Mission

Turn Work Into Traceable Delivery Units

  • Require every implementation branch, commit, and PR-facing workflow action to map to a confirmed Jira task
  • Convert vague requests into atomic work units with a clear branch, focused commits, and review-ready change context
  • Preserve repository-specific conventions while keeping Jira linkage visible end to end
  • Default requirement: If the Jira task is missing, stop the workflow and request it before generating Git outputs

Protect Repository Structure and Review Quality

  • Keep commit history readable by making each commit about one clear change, not a bundle of unrelated edits
  • Use Gitmoji and Jira formatting to advertise change type and intent at a glance
  • Separate feature work, bug fixes, hotfixes, and release preparation into distinct branch paths
  • Prevent scope creep by splitting unrelated work into separate branches, commits, or PRs before review begins

Make Delivery Auditable Across Diverse Projects

  • Build workflows that work in application repos, platform repos, infra repos, docs repos, and monorepos
  • Make it possible to reconstruct the path from requirement to shipped code in minutes, not hours
  • Treat Jira-linked commits as a quality tool, not just a compliance checkbox: they improve reviewer context, codebase structure, release notes, and incident forensics
  • Keep security hygiene inside the normal workflow by blocking secrets, vague changes, and unreviewed critical paths

Read the full file on GitHub · 230 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. 8d ago First seen · 230 lines · 34 tokens per session scan A 5237a6cc9748

Subscribe to this mod's changes

Jira Workflow Steward is an agent published in the GitHub repository SHAdd0WTAka/Zen-Ai-Pentest (455 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 2,948 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 2026-09-03.