Writing Issues

Writing Issues is a skill for Claude Code from notorious-ai/claude-plugins. It costs 72 tokens per session (1,946 once invoked), scanned A, original, MIT.

A writing guide for GitHub issues, which are records of problems, needs, and constraints in a software project.

In plain words
What is it for?
Use it to draft or revise GitHub issue titles and bodies. It covers present-progressive titles and organizing the problem around why it matters, how the situation is constrained, and what evidence shows the problem exists.
Why use it?
It helps an issue explain the problem before proposing a solution, so readers understand who is affected, what it costs, and what evidence supports it. It also separates issue writing from pull-request writing, which describes solutions.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the github-author plugin — 2 skills, 2 commands shipped together

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.

agentmods
npx agentmods add skills/notorious-ai/claude-plugins/writing-issues
Any agent
npx skills add notorious-ai/claude-plugins --skill writing-issues
Clone the repo
git clone --depth 1 https://github.com/notorious-ai/claude-plugins

Made for: Claude Code.

Or install github-author, the plugin that ships this one along with the rest of its 2 skills, 2 commands.

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 Writing Issues

README.md
[![agentmods](https://agentmods.dev/badge/skills/notorious-ai/claude-plugins/writing-issues.svg)](https://agentmods.dev/skills/notorious-ai/claude-plugins/writing-issues)
Your own site
<a href="https://agentmods.dev/skills/notorious-ai/claude-plugins/writing-issues"><img src="https://agentmods.dev/badge/skills/notorious-ai/claude-plugins/writing-issues.svg" alt="Measured on agentmods" 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 1,946 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.01946
Opus 5 $0.00036 $0.00973
Sonnet 5 $0.00014 $0.00389
Haiku 4.5 $0.00007 $0.00195

Measured 6d ago against content hash be3fb298b223, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

Writing Issues 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 6d 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.

github-author/skills/writing-issues/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Issues

An issue is a communication medium for a problem space. A pull request is the same medium for a solution space. This file describes the characteristics of an issue that communicates its problem well. It does not prescribe a structure, because the right form follows from the problem at hand, and no two problems arrive in the same shape.

The Problem-Space Trio

A problem space carries its own why, how, and what, and a good issue holds all three:

  • Why, the problem core: the friction or unmet need, who bears it, and what it costs to leave it unaddressed.
  • How, the constraints: what is already true about the world that any viable solution must operate within — operational boundaries, dependencies, deadlines, failed prior attempts, deliberate scope refusals.
  • What, the evidence: the symptoms that show the problem is real — reproductions, metrics, incident records, complaints — in the terms the affected person would use.

The solution's trio (why this design, how it is built, what it consists of) belongs to the pull request.

Effective issues communicate inside-out: why first, then how, then what. Most drafts arrive outside-in, opening with a symptom or a requested feature, and reversing that direction is usually the single largest improvement available. The mechanism is how each ordering reads: symptoms placed before the friction read as a work list; placed after it, they read as evidence.

Inside-out is a direction of emphasis, not a section order. A short bug report can lead with the symptom because triage and deduplication start there, and still carry its why in the sentence that follows.

Titles

Issues track ongoing work, and the title reflects this with a present-progressive verb: work that is happening, not a command to execute. Think: "This issue is _____ (verb+ing)."

Imperative (suits PRs) Present progressive (suits issues)
Add timezone support Supporting user timezone preferences
Fix search crash Fixing search crash on large date ranges
Implement caching Improving response times for frequent queries

Read the full file on GitHub · 71 lines

Files

What ships with it

3 files 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. 6d ago First seen · 71 lines · 72 tokens per session scan A be3fb298b223

Subscribe to this mod's changes

Writing Issues is a skill published in the GitHub repository notorious-ai/claude-plugins (5 stars, last pushed 10d ago), licensed MIT. It adds 72 tokens to every session and 1,946 once invoked, about $0.0004 per session on Opus 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens