github-issue

github-issue is a skill for Claude Code from softinio/nix-config. It costs 72 tokens per session (4,439 once invoked), scanned C, original, MIT.

A complete workflow for taking a GitHub issue from setup through implementation and a pull request. A pull request is a proposed code change for review and merging.

In plain words
What is it for?
Use it when starting work on a specific issue to create the workspace, plan and implement the fix, run tests, open a pull request, and tear down the temporary setup.
Why use it?
It organizes the required work around an issue, including a separate worktree, development setup, tests, planning, review, and cleanup.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it when starting work on a specific issue to create the workspace, plan and implement the fix, run tests, open a pull request, and tear down the temporary setup.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/softinio/nix-config/github-issue
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.

Any agent
npx skills add softinio/nix-config --skill github-issue
Clone the repo
git clone --depth 1 https://github.com/softinio/nix-config

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/softinio/nix-config/github-issue"><img src="https://agentmods.dev/badge/skills/softinio/nix-config/github-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,439 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00072 $0.04439
Opus 5.5 $0.00029 $0.01776
Sonnet 5.5 $0.00014 $0.00888
Haiku 4.5 $0.00007 $0.00444

Measured 1mo ago against content hash c0a56f288b23, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

github-issue scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf .claude/worktrees/{issue-number}-{slug}
programs/claude/skills/github-issue/SKILL.md · 363 lines

How it starts

The opening of the file, as written. The whole thing — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Issue Workflow

Full lifecycle skill for working on a GitHub issue: scaffolding, planning, implementation, PR creation, and teardown.

The issue tracker is GitHub itself, driven entirely through the gh CLI — there is no separate tracker to keep in sync. Everything the workflow records (plans, decisions, completion notes) goes on the issue or the PR.


Phase 0 — Issue & Worktree Setup

Phase 0 is mandatory and sequential. Execute Steps 1 → 6 in order, and finish all of them before any Phase 1 exploration or planning.

  • At the start of Phase 0, create one task per step (Steps 1, 1.5, 2, 3, 4, 5, 6) with TaskCreate, and flip each to in_progress then completed as you go. A skipped step must be visibly impossible.
  • Never silently skip a step. If a step genuinely does not apply, name the step and state why before continuing (e.g. "Step 5: no env setup needed, this repo has no flake").
  • The user supplying context up front — base branch, approach, constraints — feeds Step 1.5. It does not authorize jumping ahead to planning; you still run Steps 2 → 6.
  • Step 6 is easy to skip. Run herdr-workspace-layout open before leaving Phase 0. It is a no-op outside herdr, so there is no condition to evaluate first.

Step 1: Resolve the issue

If $ARGUMENTS contains an issue number (123, #123) or an issue URL:

gh issue view {number} --json number,title,body,state,labels,assignees,url
  • For a URL from another repo, pass --repo {owner}/{repo} and carry that --repo through every later gh call.
  • Display the issue title and state, and confirm with the user before proceeding.
  • If the issue is already closed, say so and ask whether to continue.

If no argument is provided:

  • Ask the user for a title and brief description.
  • Confirm the target repo (gh repo view --json nameWithOwner for the current one).
  • Create it, assigned to the user:
    gh issue create --title "{title}" --body "{description}" --assignee @me
    
  • Confirm the new issue number and URL before continuing.

Read the full file on GitHub · 363 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 · 363 lines · 72 tokens per session scan C c0a56f288b23

Subscribe to this mod's changes

github-issue is a skill published in the GitHub repository softinio/nix-config (11 stars, last pushed 25d ago), licensed MIT. It adds 72 tokens to every session and 4,439 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

gh-cli

Standardize all GitHub work via gh CLI (repos, issues, PRs, reviews, Actions, labels, releases). Trigger on any GitHub URL (incl. deep links like /pull/123, /issues/123.

alyraffauf/hoenn · 52 tokens

why

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics…

alyraffauf/hoenn · 89 tokens

technical-writing

Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.

alyraffauf/hoenn · 52 tokens

teach

Explain a body of work plainly so a person actually understands it. Runs the how and why skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.

alyraffauf/hoenn · 60 tokens

unslop

Cut AI tells from any writing. Must always apply.

alyraffauf/hoenn · 14 tokens

how

Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Can critique architecture. Use why for…

alyraffauf/hoenn · 64 tokens