draft-issue

A guided interview for writing well-structured GitHub issues, which are records of bugs, requests, tasks, or discussions in a code repository.

In plain words
What is it for?
Use it to create bug reports, feature requests, task records, or discussion topics with clear context and validation criteria.
Why use it?
It helps turn an unclear idea into a useful problem report without jumping prematurely to a solution. It also checks the repository’s issue-writing rules and templates.

Command

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 commands/notorious-ai/claude-plugins/draft-issue
Clone the repo
git clone --depth 1 https://github.com/notorious-ai/claude-plugins
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,111 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 $0.00011 $0.01111
Opus 5 $0.00005 $0.00556
Sonnet 5 $0.00002 $0.00222
Haiku 4.5 $0.00001 $0.00111

Measured 2d ago against content hash 87cc9d042bef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

draft-issue 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 2d 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/commands/draft-issue.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Draft GitHub Issue

Guide the user through creating an effective issue using the writing-issues skill. An issue lives entirely in the problem space. The interview gathers the problem's why, how, and what, then derives validation criteria from that context rather than from a guess about the solution.

Step 1: Load Conventions and Check for Issue Templates

Invoke the writing-issues skill before asking anything. The conventions govern every question below, so they load first.

Look for repository issue templates: !ls -la .github/ISSUE_TEMPLATE/ 2>/dev/null || echo "No issue templates found"

If templates exist, list them and ask user if they want to follow a template.

Step 2: Determine Issue Type

Use AskUserQuestion:

  • question: "What type of issue are you creating?"
  • header: "Issue type"
  • options:
    • Bug report (Something isn't working correctly)
    • Feature request (A new capability or enhancement)
    • Task tracking (Work that needs to be done)
    • Discussion (Exploring a decision or gathering input)

Step 3: Surface the Hidden Context

Probe for three distinct kinds of context. All three come from the problem space, and the writing-issues skill governs how each is written.

  • The friction and its cost - what breaks down or goes unmet, who bears it, and what it costs to leave it alone
  • The constraints - what any solution must live within: deadlines, operational limits, dependencies, and attempts that already failed. Put each one through the skill's constraint test before recording it.
  • The observable symptoms - the visible pain that shows the problem is real: metrics, reproductions, incident records, complaint volumes. Record the numbers the user actually has, and none they do not.

Ask type-specific questions:

Bug: What were you trying to accomplish, and what does the failure cost you? What should have happened, and what happened instead? How reproducible is it, and how often does it occur? Does anything constrain a fix, such as supported versions or data that cannot be migrated?

Read the full file on GitHub · 94 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. 2d ago First seen · 94 lines · 11 tokens per session scan A 87cc9d042bef

Subscribe to this mod's changes

draft-issue is a command published in the GitHub repository notorious-ai/claude-plugins (5 stars, last pushed 6d ago), licensed MIT. It adds 11 tokens to every session and 1,111 once invoked, about $0.0001 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.