munkel: Skill for Claude Code

.claude/skills/github-issue-workflow/SKILL.md

github-issue-workflow is a skill for Claude Code from limehq/munkel. It costs 60 tokens per session (948 once invoked), scanned A, original, MIT.

A workflow guide for starting work on a GitHub issue, where GitHub is a service for tracking code tasks and reviewing changes. It describes checking whether the issue is already assigned or linked to a draft pull request, then claiming it and opening an isolated draft pull request.

In plain words
What is it for?
Use it when taking on an issue in the munkel repository. It guides issue assignment, checking existing pull requests, creating a separate Git worktree, and linking a draft pull request to the issue.
Why use it?
It helps prevent two people from working on the same issue and makes ownership and unfinished work visible to the team.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is limehq/munkel's own configuration. It tells Claude Code how to work on munkel 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 munkel configures →

Reuse

Borrowing it

Nothing to install: this file belongs to limehq/munkel. 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/limehq/munkel/main/.claude/skills/github-issue-workflow/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/limehq/munkel

Made for: Claude Code.

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-workflow

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/limehq/munkel/github-issue-workflow"><img src="https://agentmods.dev/badge/skills/limehq/munkel/github-issue-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 948 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00060 $0.00948
Opus 5.5 $0.00024 $0.00379
Sonnet 5.5 $0.00012 $0.00190
Haiku 4.5 $0.00006 $0.00095

Measured 1mo ago against content hash 0ad543c3df9d, 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-workflow 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 1mo 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.

.claude/skills/github-issue-workflow/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Starting work on a GitHub issue

One issue → one owner → one draft PR, linked both ways. The point is that ownership and in-flight work are visible to everyone from the moment work starts, so two people never unknowingly build the same thing.

1. Before starting: is it already taken?

Never open a second branch or PR for an issue someone already owns. Check first:

gh issue view N                                              # assignee + linked PRs
gh pr list --state open --search "N in:body" \
  --json number,title,isDraft,url,headRefName

If the issue is already assigned, or an open PR (draft or not) already references it, it is taken. Stop — report what you found and coordinate with the owner, or pick a different issue. Do not start parallel work.

2. Claim the issue

Assignment is the ownership signal:

gh issue edit N --add-assignee @me      # or the relevant GitHub login

3. Set up an isolated worktree, then open a draft PR immediately

Work in a dedicated git worktree, never the shared root checkout: another Claude session may drive this checkout concurrently, and a stray checkout between two of your commands silently moves HEAD — your commit then lands on main instead of your branch. Branching from a freshly fetched origin/main into a new worktree also gives you a clean, up-to-date starting point in one move.

Open the PR before the work is finished, so the issue↔PR link exists from the start. GitHub needs at least one commit on the branch to open a PR:

git fetch origin
git branch <type>/<short-slug> origin/main                            # feat/ fix/ docs/ chore/ refactor/
git worktree add .claude/worktrees/<type>+<slug> <type>/<short-slug>  # slug = branch with / → +
cd .claude/worktrees/<type>+<slug>   # stay here: run all edits, git, and builds from inside

git commit --allow-empty -m "chore: start #N"     # or your first real commit
git push -u origin <type>/<short-slug>
gh pr create --draft --base main \
  --title "<type>: <summary>" \
  --body "Closes #N"

Read the full file on GitHub · 85 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. 1mo ago First seen · 85 lines · 60 tokens per session scan A 0ad543c3df9d

Subscribe to this mod's changes

github-issue-workflow is a skill published in the GitHub repository limehq/munkel (23 stars, last pushed 27d ago), licensed MIT. It adds 60 tokens to every session and 948 once invoked, about $0.0002 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 2026-08-30.