rhdh-jira-refine

rhdh-jira-refine is a skill for Claude Code, Codex from redhat-developer/rhdh-skills. It costs 164 tokens per session (699 once invoked), scanned A, original, Apache-2.0.

A readiness checker for existing Red Hat Developer Hub Jira work in the RHIDP, RHDHPLAN, RHDHBUGS, and RHDHSUPP workflows. It checks issues, search results, sprints, or backlogs against the rules for their current status.

In plain words
What is it for?
Use it to review Jira work and get a report of readiness problems. It can also check feature exploration work and suggest fixes when requested.
Why use it?
It shows what is missing before work moves forward, instead of relying on guesses. It can reveal missing fields, hierarchy problems, possible duplicates, unanswered comments, and stale work.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the jira plugin — 10 skills shipped together

Good fit Use it to review Jira work and get a report of readiness problems. It can also check feature exploration work and suggest fixes when requested.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhat-developer/rhdh-skills/rhdh-jira-refine
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 redhat-developer/rhdh-skills --skill rhdh-jira-refine
Clone the repo
git clone --depth 1 https://github.com/redhat-developer/rhdh-skills

Made for: Claude Code, Codex.

Or install jira, the plugin that ships this one along with the rest of its 10 skills.

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 rhdh-jira-refine

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/redhat-developer/rhdh-skills/rhdh-jira-refine"><img src="https://agentmods.dev/badge/skills/redhat-developer/rhdh-skills/rhdh-jira-refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 699 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 $0.00164 $0.00699
Opus 5 $0.00082 $0.00349
Sonnet 5 $0.00033 $0.00140
Haiku 4.5 $0.00016 $0.00070

Measured 11d ago against content hash e4fb0c4d8bd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

rhdh-jira-refine 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.

skills/jira/rhdh-jira-refine/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Refine RHDH Jira work

Answer "is this ready" with the criteria the RHDH workflow actually enforces, and say what is missing rather than guessing at it.

Route

Load workflows/refine-issues.md. It covers both the per-issue readiness audit and the Feature Exploration checklist — the same checks, applied at different points in a Feature's life.

Not gated on grilling

Unlike /rhdh-jira-create, this skill does not require the external grilling skill and must not be blocked on it. Refinement reads work that already exists. Gating it on an optional external skill would take a whole capability offline for no benefit.

Reads by default, writes only on request

The report is read-only. When the user asks for fixes, each change becomes an external write: invoke /mutation-gate and follow it. A refine pass typically proposes many small fixes at once, so state them as one set — issue key and exact command per row — rather than approving them one at a time.

Boundary with the neighbouring skills

  • Opening new work is /rhdh-jira-create.
  • Updating one known key — status, comment, assignee, link — is /rhdh-jira-update. Refinement reports across many issues; it does not replace that.
  • Building the next sprint from the refined backlog is /rhdh-jira-sprint-plan.
  • Exit criteria tables, field IDs, JQL, and the component catalog are /rhdh-jira-api.
  • Sizing scales, duplicate detection, and decomposition rules are /rhdh-jira-authoring.
  • What is still open against a release is /rhdh-release-status.

Completion

Complete when every issue the report covers was actually fetched with its custom fields enriched — an unenriched search returns empty Story Points, Team, Size, and Sprint, which looks identical to a field nobody set and is the single most common source of a false "missing data" finding. Report the JQL, the issue count, and whether the result was truncated. Every finding names the check that produced it and its severity. A field that could not be retrieved is reported as unretrieved, never as missing.

Read the full file on GitHub · 63 lines

Files

What ships with it

2 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. 11d ago First seen · 63 lines · 164 tokens per session scan A e4fb0c4d8bd9

Subscribe to this mod's changes

rhdh-jira-refine is a skill published in the GitHub repository redhat-developer/rhdh-skills (16 stars, last pushed 2d ago), licensed Apache-2.0. It adds 164 tokens to every session and 699 once invoked, about $0.0008 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