agentic-coding: Skill for Claude Code

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

github-issue-solve is a skill for Claude Code, Codex from P2ERGmbH/agentic-coding. It costs 29 tokens per session (2,664 once invoked), scanned A, original, MIT.

A workflow for resolving a GitHub issue, which is a task or bug report in a code repository, by changing the project locally and preparing a pull request. A pull request is a proposed code change for review.

In plain words
What is it for?
Use it when you have a specific issue number and want to investigate it, create a branch, implement the fix, verify it, and open a pull request.
Why use it?
It organizes the work from understanding the issue through implementation, testing, and review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; positional $N argument; 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-solve/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-solve

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/p2ergmbh/agentic-coding/github-issue-solve"><img src="https://agentmods.dev/badge/skills/p2ergmbh/agentic-coding/github-issue-solve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,664 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 $0.00029 $0.02664
Opus 5.5 $0.00012 $0.01066
Sonnet 5.5 $0.00006 $0.00533
Haiku 4.5 $0.00003 $0.00266

Measured 2mo ago against content hash 86fefa98c09a, 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-solve 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-solve/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Issue Workflow

This workflow guides you through resolving a GitHub issue locally. It is based on a robust, CLI-agnostic automation framework.

Role & Persona

You are an expert software engineer and autonomous agent.

Trigger

Use this workflow whenever the user asks to "handle," "solve," "resolve," or "work on" a GitHub issue.


Phase 1: Context Setup & Identification

  1. Identify Issue Number: Check the current conversation and environment.
    • If the issue number is found (e.g., "#123"), proceed.
    • If NOT found, STOP and ask the user: "Could you please provide the GitHub issue number you'd like me to work on?"
  2. Fetch Details: Once the issue number (referred to as $ISSUE_NUMBER) is known, run:
    gh issue view $ISSUE_NUMBER
    
  3. Validate Requirements: Analyze the issue description for a CLEAR GOAL and SUCCESS CRITERIA.
    • IF UNCLEAR:
      1. Comment on the issue: gh issue comment $ISSUE_NUMBER --body "..." asking for the missing Goal, Success Criteria, or Context.
      2. Inform the user you are waiting for clarification and STOP.
    • IF CLEAR: Proceed to Phase 2.
      1. Assign yourself to the issue: gh issue edit $ISSUE_NUMBER --add-assignee "@me".
      2. Comment on the issue: gh issue comment $ISSUE_NUMBER --body "..." stating the start of work and what branch is being used.
  4. Internalize rules: read all docs/rules/*.md files and apply the rules defined there to the following steps
  5. Figma Designs: If the issue description contains a link to a Figma design, you MUST activate the figma-implement skill using activate_skill to get instructions on how to handle Figma to code conversion.

Phase 2: Initialization & Branching

  1. Sync with Main First: Ensure you are starting from the latest state:
    • git checkout main
    • git pull origin main
  2. Define Branch: Target branch name is feat/$ISSUE_NUMBER-by-cli-agent-<short-description>.
    • Replace <short-description> with a brief, kebab-case summary of the issue (e.g., feat/811-by-cli-agent-improve-x-and-y).
  3. Check/Switch Branch:
    • Check if it exists: git branch --list "*$ISSUE_NUMBER*"
    • If it exists, checkout: git checkout [matching-branch-name]
    • If NOT, create it from the updated main: git checkout -b feat/$ISSUE_NUMBER-by-cli-agent-<short-description>

Read the full file on GitHub · 124 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 · 124 lines · 29 tokens per session scan A 86fefa98c09a

Subscribe to this mod's changes

github-issue-solve is a skill published in the GitHub repository P2ERGmbH/agentic-coding (9 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 2,664 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.