A command for managing a repository's issue records in an `.issues/` folder. An issue is a written record of a task, problem, or proposed change.

Use `/issue` to initialize issue tracking in a project and manage the documented workflow for individual issues.

It keeps issue details, plans, progress notes, review instructions, and completion summaries together in a predictable format.

issue — Command by JSMike

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/jsmike/ai-workflow-starter/issue

Clone the repo

git clone --depth 1 https://github.com/JSMike/ai-workflow-starter

Made for: Claude Code.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,956 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.

Model	Per session	Once invoked
Fable 5	$0.00008	$0.02956
Opus 5	$0.00004	$0.01478
Sonnet 5	$0.00002	$0.00591
Haiku 4.5	$0.00001	$0.00296

Measured 2d ago against content hash 0953878dcf84, 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/issue.md · 455 lines

How it starts

The opening of the file, as written. The whole thing — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Management

Manage the issue tracking system in .issues/. This command is portable and can bootstrap issue tracking in any repository.

Usage: /issue <action> [arguments]

Actions

init

Initialize the .issues/ folder structure in a new project.

Create .issues/ directory
Create .issues/README.md with conventions documentation (template below)
Create empty .issues/index.md with header

README.md Template:

# Issue Tracking

This folder contains issue tracking for the repository. Each issue has its own folder with documentation.

Canonical workflow rules live in `../AGENTS.md`. Keep this file focused on `.issues/` folder conventions.

## Structure

Each `ISSUE-N/` folder contains:
- `issue.md` - Requirements and metadata (always present)
- `plan.md` - Implementation approach (created when planning)
- `session-log.md` - Append-only session progress records
- `qa-instructions.md` - Step-by-step human validation guide (created when moving to review)
- `summary.md` - Final completion record (created after verification)

## Status Values

| Status | Meaning |
|--------|---------|
| idea | Captured thought, exploration, or vague request; not yet scoped |
| backlog | Scoped but not ready to work |
| ready | Ready to work, dependencies met, acceptance criteria clear |
| in-progress | Currently being worked on |
| review | Implementation complete, awaiting verification |
| done | Verified working and accepted |

## Metadata Fields

| Field | Description |
|-------|-------------|
| Status | Current status (see above) |
| Owner | Agent / TBD / person name |
| Created | Date created (YYYY-MM-DD) |
| Source | Origin category (design-review, bug-report, etc.) |
| External | External ticket reference (optional) |
| Blocks | Issues this blocks (optional) |
| Blocked-by | Issues blocking this (optional) |
| Priority | high / medium / low |

## Commands

Use `/issue <action>` to manage issues:
- `init` - Initialize this folder structure
- `create <title>` - Create new issue
- `match <description>` - Find existing issues matching a description
- `work <id>` - Start working on an issue
- `list [status]` - Show issues
- `show <id>` - Display issue details
- `status <id> <status>` - Update status
- `plan <id>` - Create/update plan
- `session <id>` - Append session progress (run at end of each work session or before handoff)
- `done <id>` - Mark verified work complete with comprehensive summary
- `delete <id>` - Remove issue
- `index` - Regenerate index.md

## Lifecycle

1. Clarify vague requests before creating implementation-ready issues
2. Create issue with `/issue create`
3. Plan implementation, add plan.md
4. Work on issue, update status to `in-progress`
5. **After each work session or before handoff, run `/issue session` to append progress to `session-log.md`** (mandatory)
6. When implementation is complete, create `qa-instructions.md` and set status to `review`
7. After verification, run `/issue done` for final summary
8. After PR merge, run `/issue delete`

**Important:** Session log entries are mandatory for each work session or handoff point, not optional. One entry can cover multiple related edits in the same uninterrupted work session. The audit trail depends on consistent session recording.

## Session Log Template

Append each work session to `ISSUE-N/session-log.md` using this structure:

- `# Session N`
- `**Date:** YYYY-MM-DD`
- `**Prompt/Ask:**` Briefly state the user request that triggered this work.
- `## Completed`
- `## Current Status`
- `## Plan Coverage`
- `## Files Changed`
- `## Verification`
- `## Next Steps`

Read the full file on GitHub · 455 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.

2d ago First seen · 455 lines · 8 tokens per session scan A 0953878dcf84

Subscribe to this mod's changes

issue is a command published in the GitHub repository JSMike/ai-workflow-starter (2 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 2,956 once invoked, about $0.0000 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.

Project management

template

Manage issue templates for streamlined issue creation.

gastownhall/beads · 0 tokens

speckit.auto

Automatically execute the four core phases of the Spec-Driven Development (SDD) pipeline: specify → plan → tasks → implement, in strict sequential order.

VisActor/VChart · 31 tokens

daily-priorities

Query DIGI Jira via the Atlassian MCP to build a prioritized daily work plan. The report has two parts: suggested priorities (the recommendation) and full context (everything you need to evaluate whether the suggestions are right and what else is on the docket).

DIGI-UW/OpenELIS-Global-2 · 0 tokens

issue