granite.build: Command for Claude Code

.claude/commands/create-issues.md

create-issues is a command for Claude Code from ibm-granite/granite.build. It costs 25 tokens per session (1,125 once invoked), scanned A, original, Apache-2.0.

A command that reads an architecture document and turns it into a hierarchy of GitHub issues: a large project item, milestone groups, and implementation tasks. Architecture documents describe how a software system is organised and built.

In plain words
What is it for?
Use it to create structured GitHub issues from an architecture document in a forked repository.
Why use it?
It converts a broad technical plan into smaller trackable work items with milestones, acceptance checks, and affected files.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool.

This is ibm-granite/granite.build's own configuration. It tells Claude Code how to work on granite.build 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 granite.build configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ibm-granite/granite.build. 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/ibm-granite/granite.build/main/.claude/commands/create-issues.md
Clone the repo
git clone --depth 1 https://github.com/ibm-granite/granite.build

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 create-issues

README.md
[![agentmods](https://agentmods.dev/badge/commands/ibm-granite/granite.build/create-issues.svg)](https://agentmods.dev/commands/ibm-granite/granite.build/create-issues)
Your own site
<a href="https://agentmods.dev/commands/ibm-granite/granite.build/create-issues"><img src="https://agentmods.dev/badge/commands/ibm-granite/granite.build/create-issues.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,125 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.
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 $0.00025 $0.01125
Opus 5 $0.00013 $0.00562
Sonnet 5 $0.00005 $0.00225
Haiku 4.5 $0.00003 $0.00112

Measured 2d ago against content hash 6806bdc9768b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Implementation Issues from Architecture Document

You are helping a developer turn an architecture/design document into a structured set of GitHub issues. The issues are created in the fork repo (derived from origin remote).

Architecture document path: $ARGUMENTS

Step 0: Validate input

If $ARGUMENTS is empty or the file does not exist, ask the user to provide a valid path:

Usage: /create-issues <path-to-architecture-document>
Example: /create-issues docs/plans/2026-02-23-architecture.md

Do not proceed until a valid path is provided.

Step 1: Read and analyze the document

  1. Read the architecture document at the given path
  2. Identify the top-level structure:
    • Document title and overall goal
    • Milestones (major sections, typically ## Milestone N: ...)
    • Sub-steps within each milestone (typically ### N.M ...)
    • Verification/acceptance criteria per milestone
    • Files to create or modify per milestone
  3. Derive the fork owner and repo:
    FORK_OWNER=$(git remote get-url origin | sed -E 's|.*[:/]([^/]+)/.*|\1|')
    FORK_REPO=$(git remote get-url origin | sed -E 's|.*[:/][^/]+/(.*)(.git)?$|\1|' | sed 's/\.git$//')
    

Step 2: Decide granularity and propose issue plan

For each milestone, decide whether sub-steps should be individual issues or grouped:

  • Split into separate issues when sub-steps are independent, touch different files, and are substantial enough to be a standalone PR
  • Group into one issue when sub-steps are tightly coupled, touch the same files, or are small enough to implement together

Present the proposed issue hierarchy to the user:

Epic: <document title>
  Milestone 1: <title>
    - Issue: <description>
    - Issue: <description>
  Milestone 2: <title>
    - Issue: <description>
    ...

Ask the user to approve or adjust the plan before creating any issues. Use AskUserQuestion.

Step 3: Create issues bottom-up

Create issues in this order so parent issues can reference child issue numbers:

Read the full file on GitHub · 160 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 · 160 lines · 25 tokens per session scan A 6806bdc9768b

Subscribe to this mod's changes

create-issues is a command published in the GitHub repository ibm-granite/granite.build (44 stars, last pushed 2d ago), licensed Apache-2.0. It adds 25 tokens to every session and 1,125 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 2026-09-04.