issue

A command that creates a carefully labeled GitHub issue describing upcoming work.

In plain words
What is it for?
Use it to check repository state, search for existing issues, gather relevant project documentation, and open a new issue with dependencies and required labels.
Why use it?
It reduces duplicate issues and ensures later planning or implementation has the necessary context, labels, and related-work information.

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/jayminwest/kotadb/issue
Clone the repo
git clone --depth 1 https://github.com/jayminwest/kotadb

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 825 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 $0.00000 $0.00825
Opus 5 $0.00000 $0.00413
Sonnet 5 $0.00000 $0.00165
Haiku 4.5 $0.00000 $0.00082

Measured 2d ago against content hash 0548db380bde, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

.claude/commands/issues/issue.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Issue Creation

Template Category: Action Prompt Level: 3 (Conditional)

Create a rigorously labeled GitHub issue capturing the upcoming work. Follow this sequence so downstream commands (plan, implement) have complete context.

Steps

  1. Sync repo state
    • git fetch --all --prune
    • git status --short (ensure clean working tree before opening an issue)
  2. Avoid duplicates
    • gh issue list --search "<keywords>" --state all
    • If a related issue exists, link and update instead of creating a duplicate.
  3. Confirm label taxonomy (MANDATORY)
    • gh label list --limit 100
    • Ensure you have one label from each required category: component, priority, effort, status. Add optional methodology/risk labels if useful.
  4. Collect context
    • Review .claude/commands/docs/conditional_docs/app.md or .claude/commands/docs/conditional_docs/automation.md and open only the docs whose conditions match the work (e.g., README.md, CLAUDE.md, .claude/.cache/specs/**).
    • Capture reproduction steps or business justification as needed.
    • Identify issue relationships: Check for dependencies, related work, blockers using .claude/commands/docs/issue-relationships.md
      • gh issue list --search "<keywords>" to find related issues
      • Review recent spec files in .claude/.cache/specs/ for relationship patterns
      • Check git history or PRs for prerequisite work
  5. Draft issue content
    • Include sections for Description, Acceptance Criteria, Technical Approach (if known), Validation, and References.
    • Add Issue Relationships section if any dependencies/relationships exist (see .claude/commands/docs/issue-relationships.md)
    • Keep titles Conventional Commit compatible (e.g., feat: describe capability).
  6. Create the issue
    • gh issue create --title "<title>" --body-file <temp-body.md> --label "component:...,priority:...,effort:...,status:..."
    • Label requirements: MUST include at least one label from each category:
      • Component: backend, api, database, testing, ci-cd, documentation, observability
      • Priority: critical, high, medium, low
      • Effort: small, medium, large
      • Status: needs-investigation, blocked, in-progress, ready-review
    • Example: --label "component:backend,priority:medium,effort:small,status:needs-investigation"
    • Record the returned issue number for downstream commands. Store it in your notes.
  7. Verify issuance and labels
    • gh issue view <number> to confirm labels, body, assignee, and milestone.
    • Verify all four label categories are present: component, priority, effort, status
    • If labels are missing, add them immediately: gh issue edit <number> --add-label "missing:labels"

Read the full file on GitHub · 78 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 · 78 lines · 0 tokens per session scan A 0548db380bde

Subscribe to this mod's changes

issue is a command published in the GitHub repository jayminwest/kotadb (102 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 825 tokens. 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.