create-issues

A command that turns a feature request or GitHub issue into a structured implementation plan with product requirements and test-based acceptance criteria. GitHub issues are records of bugs, tasks, or proposed changes in a repository.

In plain words
What is it for?
Planning features from written descriptions, GitHub issue links, or issue numbers, then organising the work into trackable implementation tasks.
Why use it?
It breaks an unclear request into concrete work that developers can implement and verify.

Command for Claude Code

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/wbern/agent-instructions/create-issues
Clone the repo
git clone --depth 1 https://github.com/wbern/agent-instructions

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,320 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 $0.00018 $0.01320
Opus 5 $0.00009 $0.00660
Sonnet 5 $0.00004 $0.00264
Haiku 4.5 $0.00002 $0.00132

Measured 2d ago against content hash a35145e0bff8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-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 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.

.claude/commands/create-issues.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Issues: PRD-Informed Task Planning for TDD

Create structured implementation plan that bridges product thinking (PRD) with test-driven development.

General Guidelines

Output Style

  • Never explicitly mention TDD in code, comments, commits, PRs, or issues
  • Write natural, descriptive code without meta-commentary about the development process
  • The code should speak for itself - TDD is the process, not the product

Beads is available for task tracking. Use mcp__beads__* tools to manage issues (the user interacts via bd commands).

Plan File Restriction

NEVER create, read, or update plan.md files. Claude Code's internal planning files are disabled for this project. Use other methods to track implementation progress (e.g., comments, todo lists, or external tools).

User arguments:

Create-issues: $ARGUMENTS

End of user arguments

(If no input provided, check conversation context or run bd ready to see existing work)

Input Processing

The input can be one of:

  1. GitHub Issue URL (e.g., https://github.com/owner/repo/issues/123)
  2. GitHub Issue Number (e.g., #123 or 123)
  3. Feature Description (e.g., "Add user authentication")
  4. Empty - use conversation context

GitHub Issue Integration

If input looks like a GitHub issue:

Step 1: Extract Issue Number

  • From URL: extract owner/repo/number
  • From number: try to infer repo from git remote
  • From branch name: check patterns like issue-123, 123-feature, feature/123

Step 2: Fetch Issue

Try to fetch the issue using GitHub MCP (mcp__github__issue_read tool).

If GitHub MCP is not configured, show:

GitHub MCP not configured!
See: https://github.com/modelcontextprotocol/servers/tree/main/src/github
Trying GitHub CLI fallback...

Then try using gh issue view [ISSUE_NUMBER] --json as fallback.

Step 3: Use Issue as Discovery Input

  • Title → Feature name
  • Description → Problem statement and context
  • Labels → Type/priority hints
  • Comments → Additional requirements and discussion
  • Linked issues → Dependencies

Read the full file on GitHub · 206 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 · 206 lines · 18 tokens per session scan A a35145e0bff8

Subscribe to this mod's changes

create-issues is a command published in the GitHub repository wbern/agent-instructions (168 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 1,320 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 2026-08-30.