A command that finds the next open GitHub issue, or loads a specific issue, and begins a guided implementation process. GitHub issues are tracked work items such as bugs, features, and tasks.

Use it to inspect the current milestone, open and closed issues, branch status, and repository changes before implementing an issue.

It gathers the issue, milestone, branch, and working-tree context an agent needs before changing code. This reduces the chance of starting the wrong task or overlooking related work.

next-issue — Command by refo

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/refo/claude-dev-helpers/next-issue

Clone the repo

git clone --depth 1 https://github.com/refo/claude-dev-helpers

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,248 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 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	$0.00029	$0.01248
Opus 5	$0.00015	$0.00624
Sonnet 5	$0.00006	$0.00250
Haiku 4.5	$0.00003	$0.00125

Measured 2d ago against content hash c70b787e5c1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

next-issue scanned grade C with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Project helpers config (if present): !`cat .claude/helpers.json 2>/dev/null || echo "no helpers.json — proceed with generic defaults; do not run any dev/watch processes unless the user asks"`

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- **Do not run any command listed in `doNotRun`** in `helpers.json` (typically dev/watch servers the user keeps running themselves).

plugins/dev-helpers/commands/next-issue.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Next Issue

Context

Project helpers config (if present): !cat .claude/helpers.json 2>/dev/null || echo "no helpers.json — proceed with generic defaults; do not run any dev/watch processes unless the user asks"
Current active milestone: !gh api 'repos/{owner}/{repo}/milestones?state=open&sort=due_on&direction=asc' --jq '.[0].title // "no open milestone"'
Open issues in current milestone: !gh api 'repos/{owner}/{repo}/milestones?state=open&sort=due_on&direction=asc' --jq '.[0].title' | xargs -I {} gh issue list --milestone {} --state open --json number,title,labels --jq '.[] | "#\(.number) [\(.labels | map(.name) | join(","))] \(.title)"'
Closed issues in current milestone (for dependency tracking): !gh api 'repos/{owner}/{repo}/milestones?state=open&sort=due_on&direction=asc' --jq '.[0].title' | xargs -I {} gh issue list --milestone {} --state closed --json number --jq '.[] | "#\(.number)"'
Current branch: !git branch --show-current
Working tree status: !git status --short

Arguments

User provided: $ARGUMENTS

Instructions

This is a session-starter skill. Its purpose is to load an issue into context and begin the grill-then-implement flow. Decisions first, code second.

1. Pick the issue

If an issue number was provided as an argument (e.g. 5, #5, or 3): use that issue. Run gh issue view <number> to load its full body.
If no argument was provided: pick the lowest-numbered open issue in the current milestone whose dependencies are all closed.
- Look at each candidate issue's "Depends on" section (referenced issue numbers like #1, #4).
- If any referenced issue is still open, the candidate is blocked — skip it.
- Use the first unblocked one.
- If all open issues are blocked, tell the user which blocker(s) are in the way and stop.

2. Announce the pick

Show the user:

Issue number and title
Labels (area / module / kind)
A one-line summary of what this issue is about

3. Load the full body and surface design questions

Read the full file on GitHub · 99 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 · 99 lines · 29 tokens per session scan C c70b787e5c1d

Subscribe to this mod's changes

next-issue is a command published in the GitHub repository refo/claude-dev-helpers (2 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 1,248 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Debugging Git and workflow

next-issue