github-issue-refine

A workflow for improving an existing GitHub issue, which is a task or bug report stored in a code repository. It checks the issue’s goal, implementation details, missing context, and project rules.

In plain words
What is it for?
Use it to refine feature requests, bug reports, and development tickets. It helps clarify success criteria, technical steps, interface constraints, and testing plans.
Why use it?
It removes vague or incomplete instructions before development starts, reducing misunderstandings and rework.

Skill for Claude CodeCodex

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/p2ergmbh/agentic-coding/github-issue-refine
Any agent
npx skills add P2ERGmbH/agentic-coding --skill github-issue-refine
Clone the repo
git clone --depth 1 https://github.com/P2ERGmbH/agentic-coding

Made for: Claude Code, Codex.

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,398 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 $0.00027 $0.01398
Opus 5 $0.00014 $0.00699
Sonnet 5 $0.00005 $0.00280
Haiku 4.5 $0.00003 $0.00140

Measured 2d ago against content hash ecf686ba60b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-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 2d 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.

.agents/skills/github-issue-refine/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Issue Refinement Workflow

This workflow guides you through refining an existing GitHub issue to improve its clarity, technical implementation details, and alignment with project rules.

Trigger

Use this workflow when the user asks to "refine an issue," "improve a ticket," "groom a task," or "update the issue description."


Phase 1: Research & Validation

  1. Fetch Issue Details:
    • Retrieve the issue details: gh issue view $ISSUE_NUMBER
  2. Analyze Current State:
    • Identify the core goal and success criteria.
    • Assess if the current implementation plan is specific enough.
    • Check for missing contexts (UI constraints, etc.).
  3. Cross-Reference docs/rules:
    • Verify that the proposed solution aligns with:
      • next.md: Are Server Actions and Client/Server component rules followed?
      • ui.md & icons.md: Is the component and icon usage correct?
      • testing.md: Is there a clear strategy for Vitest?
      • figma.md: Explicitly read this file to ensure Figma implementations adhere to the parsing rules, cleanup requirements, and master component references.

Phase 2: Technical Refinement

  1. Improve Implementation Steps:
    • Refine generic steps into specific actions tied to concrete files and functions.
    • Ensure every step has a "Reason" explaining WHY it's necessary.
  2. Add Additional Context:
    • Examples: Provide snippets of expected data structures or code patterns.
    • Diagrams: Use Mermaid syntax for complex state transitions or data flows.
    • Documentation: Reference specific documentation paths (e.g., from nextjs_docs) relevant to the implementation.
  3. Deep File Investigation:
    • Use list_code_definition_names or search_files to find related logic that might be affected but wasn't mentioned in the original issue.
  4. Visual Context & Attachments:
    • Current State: If possible, use browser automation tools to take a screenshot of the current state of the application (the "before" state). Ensure you clean up your browser session afterward by closing the opened pages using mcp_chrome-devtools_list_pages and mcp_chrome-devtools_close_page.
    • Figma Design: If a Figma layout link is provided in the issue, use the Figma MCP tool to download an image of the Figma frame to visually demonstrate what the design should be (the "after" state).
    • Issue Update & Image Hosting: Because gh CLI cannot directly upload images to issues, create a new branch named assets/issue-$ISSUE_NUMBER. Push the downloaded images to .github/assets/issue-$ISSUE_NUMBER/ on that branch. Then, update the issue description with standard Markdown image links using the GitHub blob URL with ?raw=true (e.g., ![alt](https://github.com/OWNER/REPO/blob/assets/issue-$ISSUE_NUMBER/.github/assets/issue-$ISSUE_NUMBER/image.png?raw=true)). This ensures the images render correctly even in private repositories.

Read the full file on GitHub · 92 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. 2d ago First seen · 92 lines · 27 tokens per session scan A ecf686ba60b7

Subscribe to this mod's changes

github-issue-refine is a skill published in the GitHub repository P2ERGmbH/agentic-coding (9 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 1,398 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens