agentic-coding: Skill for Claude Code

.agents/skills/github-issue-refine/SKILL.md

github-issue-refine is a skill for Claude Code, Codex from P2ERGmbH/agentic-coding. It costs 27 tokens per session (1,398 once invoked), scanned A, original, MIT.

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

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is P2ERGmbH/agentic-coding's own configuration. It tells Claude Code and Codex how to work on agentic-coding itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentic-coding configures →

Reuse

Borrowing it

Nothing to install: this file belongs to P2ERGmbH/agentic-coding. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/P2ERGmbH/agentic-coding/main/.agents/skills/github-issue-refine/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/P2ERGmbH/agentic-coding

Made for: Claude Code, Codex.

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 github-issue-refine

README.md
[![agentmods](https://agentmods.dev/badge/skills/p2ergmbh/agentic-coding/github-issue-refine/github.svg)](https://agentmods.dev/skills/p2ergmbh/agentic-coding/github-issue-refine)
Your own site
<a href="https://agentmods.dev/skills/p2ergmbh/agentic-coding/github-issue-refine"><img src="https://agentmods.dev/badge/skills/p2ergmbh/agentic-coding/github-issue-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 github-issue-refine

Your own site · 80×15
<a href="https://agentmods.dev/skills/p2ergmbh/agentic-coding/github-issue-refine"><img src="https://agentmods.dev/badge/skills/p2ergmbh/agentic-coding/github-issue-refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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. 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 $0.00027 $0.01398
Opus 5.5 $0.00011 $0.00559
Sonnet 5.5 $0.00005 $0.00280
Haiku 4.5 $0.00003 $0.00140

Measured 2mo ago against content hash ecf686ba60b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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. 2mo 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 4mo ago), licensed MIT. It adds 27 tokens to every session and 1,398 once invoked, about $0.0001 per session on Opus 5.5. 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.