agentic-coding: Skill for Claude Code

.agents/skills/github-sub-issue-add/SKILL.md

github-sub-issue-add is a skill for Claude Code, Codex from P2ERGmbH/agentic-coding. It costs 24 tokens per session (1,459 once invoked), scanned A, original, MIT.

A procedure for using GitHub’s API to create or link a smaller sub-issue under an existing main issue, and to record which issues depend on others.

In plain words
What is it for?
Use it to add a new or existing sub-issue to a parent issue or establish a blocking relationship between issues.
Why use it?
It avoids confusing GitHub’s issue number with its other internal identifiers, which can cause API requests to target the wrong issue.

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-sub-issue-add/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-sub-issue-add

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/p2ergmbh/agentic-coding/github-sub-issue-add"><img src="https://agentmods.dev/badge/skills/p2ergmbh/agentic-coding/github-sub-issue-add.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,459 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 $0.00024 $0.01459
Opus 5.5 $0.00010 $0.00584
Sonnet 5.5 $0.00005 $0.00292
Haiku 4.5 $0.00002 $0.00146

Measured 2mo ago against content hash 240fae0ee3a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github-sub-issue-add 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/github-sub-issue-helper.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-sub-issue-add/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add Sub-Issue to GitHub Main/Parent Issue

This skill allows creating a new sub-issue or linking an existing issue as a sub-issue to a parent/main issue using the official GitHub REST API (API version 2026-03-10). It also supports establishing issue dependencies (blocking relationships).


⚠️ CRITICAL CONCEPT: GitHub Identifiers

To perform sub-issue or dependency operations, you MUST understand and handle the difference between GitHub's distinct identifier types:

  1. Issue Number (e.g., 2396):
    • A human-friendly sequential integer unique within a single repository.
    • Used in URLs, markdown references (#2396), and standard CLI commands (gh issue view 2396).
  2. GraphQL Global Node ID (e.g., "I_kwDOP0rKb88AAAABFCwpYA"):
    • A globally unique string identifier.
    • WARNING: In the gh CLI, calling gh issue view <number> --json id or gh issue list --json id returns this string Node ID, NOT the numerical database ID!
  3. Numerical REST Database ID (e.g., 4633405792):
    • A globally unique numerical integer used by GitHub's relational database.
    • CRITICAL: The REST API endpoints for sub-issues and dependencies (under API version 2026-03-10) require this numerical Database ID in their JSON payloads. Passing the sequential Issue Number or the string GraphQL Global Node ID will result in validation errors (typically 404 Not Found or 422 Unprocessable Entity).

To automate ID resolution, API calls, and handle fallbacks gracefully, always use the workspace helper script:

Link Sub-Issue to Parent:

npx node .agents/skills/github-sub-issue-add/scripts/github-sub-issue-helper.js add --parent <parent-issue-number> --sub <sub-issue-number>

Establish Issue Dependency (Blocking Relationship):

npx node .agents/skills/github-sub-issue-add/scripts/github-sub-issue-helper.js dependency --dependent <dependent-issue-number> --blocking <blocking-issue-number>

Read the full file on GitHub · 149 lines

Files

What ships with it

1 file 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. 2mo ago First seen · 149 lines · 24 tokens per session scan A 240fae0ee3a5

Subscribe to this mod's changes

github-sub-issue-add is a skill published in the GitHub repository P2ERGmbH/agentic-coding (9 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 1,459 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.