jira-issue-refine

jira-issue-refine is a skill for Claude Code from yarlson/yarstack. It costs 63 tokens per session (1,306 once invoked), scanned A, original, MIT.

A process for refining one Jira issue into a bounded delivery contract. Jira is a system for tracking engineering work, and the contract explains the required outcome, scope, evidence, dependencies, and risks.

In plain words
What is it for?
Use it to review a draft or existing issue, separate confirmed requirements from assumptions, identify missing decisions, and produce a clear implementation-ready issue without implementing it.
Why use it?
It removes ambiguity before handoff so an engineer or coding agent does not have to guess what the issue means or what counts as complete.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the yarstack plugin — 40 skills shipped together

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 skills/yarlson/yarstack/jira-issue-refine
Any agent
npx skills add yarlson/yarstack --skill jira-issue-refine
Clone the repo
git clone --depth 1 https://github.com/yarlson/yarstack

Made for: Claude Code.

Or install yarstack, the plugin that ships this one along with the rest of its 40 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 jira-issue-refine

README.md
[![agentmods](https://agentmods.dev/badge/skills/yarlson/yarstack/jira-issue-refine.svg)](https://agentmods.dev/skills/yarlson/yarstack/jira-issue-refine)
Your own site
<a href="https://agentmods.dev/skills/yarlson/yarstack/jira-issue-refine"><img src="https://agentmods.dev/badge/skills/yarlson/yarstack/jira-issue-refine.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,306 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 5.1 $0.00063 $0.01306
Opus 5 $0.00032 $0.00653
Sonnet 5 $0.00013 $0.00261
Haiku 4.5 $0.00006 $0.00131

Measured 6d ago against content hash 5ee3037a4a0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

jira-issue-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 6d 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.

plugins/yarstack/skills/jira-issue-refine/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jira Issue Refinement

Turn one issue into a concise contract that an engineer or coding agent can implement and verify without guessing. Preserve confirmed intent, resolve discoverable facts, and expose decisions that still require a person.

Establish the issue boundary

  1. Read the complete draft or existing issue, including structured fields, comments, links, attachments, parent or child issues, and user-supplied context when available.
  2. Identify the affected actor or system, current behavior, required outcome, business or operational reason, and requested issue type.
  3. Separate confirmed requirements from observations, assumptions, implementation suggestions, and unrelated follow-up ideas. Do not silently promote an engineering suggestion into required behavior.
  4. Preserve the author's confirmed intent and terminology. Change meaning only when evidence or an explicit user decision requires it.
  5. Keep Jira access read-only unless the user explicitly authorizes creating or updating an issue. Do not implement the requested product or engineering change under this skill.

Assess what the issue still needs

Check each concern only to the depth material to delivery:

  • Behavior: State the observable result, inputs or preconditions, boundaries, failure behavior, and unchanged behavior. Do not reward detail that merely prescribes an implementation.
  • Evidence: For a bug, capture observed and expected behavior, reproduction, environment, diagnostics, and regression evidence. For a feature, capture concrete scenarios and constraints. For infrastructure or data work, capture current and target state, ordering, idempotency, recovery, and rollback constraints.
  • Ownership: Identify the owning repository and component from authoritative evidence. Record a multi-repository dependency explicitly; do not force uncertain ownership into one repository.
  • Verification: Define deterministic evidence that will prove success and important failure or regression behavior. Prefer established repository tests, builds, static checks, and CI. Do not demand a new exact-value test for a simple declarative or version update when native checks already prove the contract.
  • Scope: Keep one coherent outcome with a clear completion boundary. Separate an epic, open-ended investigation, rewrite, or independently deliverable changes into linked issues when they do not need one atomic delivery.
  • Independence: Expose unresolved product decisions, unavailable inputs, other-team actions, external systems, sequencing, credentials, or access that can block delivery.
  • Safety: State relevant trust boundaries, state changes, compatibility constraints, rollout, rollback, and recovery needs. Treat authentication, authorization, tenant isolation, billing, personal data, migrations, public contracts, infrastructure, secrets, and destructive actions conservatively.
  • Environment: Confirm that a coding workflow can make the change and obtain credible verification locally or through established CI. Name essential runtimes, services, platforms, test data, or privileged capabilities only when they materially apply.
  • Effort: Keep the issue small enough for one focused delivery. Split work whose exploration, implementation, or validation has independent completion boundaries.

Read the full file on GitHub · 71 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. 6d ago First seen · 71 lines · 63 tokens per session scan A 5ee3037a4a0a

Subscribe to this mod's changes

jira-issue-refine is a skill published in the GitHub repository yarlson/yarstack (3 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 1,306 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 2026-08-31.

Related

Other skills, from other repositories

opensrc

Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…

vercel-labs/opensrc · 103 tokens

release-cli

Release a new version of the tokenmaxxing CLI to npm. Use when explicitly asked to release or publish @851-labs/tokenmaxxing, including checking main, bumping apps/cli/package.json, updating CHANGELOG.md, committing, tagging cli-vX.Y.Z, pushing, monitoring generated native package publishing, and smoke testing the…

851-labs/tokenmaxxing · 73 tokens

ship-mobile-app

Build, change, debug, and prepare production mobile apps across domain meaning, local and server state, lifecycle, platform, and release boundaries. Use for non-trivial Flutter, React Native, iOS, or Android work involving persistence, sync, auth, offline behavior, notifications, permissions, native integrations…

aiopshwang/ship-mobile-app · 103 tokens

verify-regression-tests

Verify that a regression test actually detects the defect it claims to guard against. Use after adding or reviewing a bug-fix guard, reproducing the original failure after a fix, or investigating a suspiciously green regression test. Do not use for general TDD, broad test-suite audits, mutation-score optimization…

aiopshwang/verify-regression-tests · 75 tokens

fable-mode

MANDATORY before diagnosing any bug, debugging any failure, reviewing code, or making a non-trivial change — invoke FIRST, before reading code or proposing a cause; do not skip because the task "looks simple". Five-gate rigor protocol (scope, evidence, attack, verify, report) with per-task playbooks and tripwires.…

davesheffer/hunch · 108 tokens

repository-bootstrap

Audit and establish or upgrade the canonical repository governance baseline. Use only when explicitly asked to bootstrap, standardize, or upgrade a repository; do not use for feature development or source-code restructuring.

cz1993/vibe-coding-repository-standard · 41 tokens