issue-train

issue-train is a skill for Claude Code from big-emotion/agent-atelier. It costs 57 tokens per session (7,070 once invoked), scanned A, original, MIT.

A workflow for processing every open GitHub issue in a list. An issue is a tracked bug, request, or task; the workflow checks its status and can connect remaining work to new pull requests.

In plain words
What is it for?
Use it to triage issues, find related open or merged pull requests, close issues that no longer apply, and create one linked pull request for each remaining task.
Why use it?
It helps separate stale or already-solved issues from work that still needs implementation and keeps issues linked to the changes that address them.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions subagents.

Part of the pr-trains plugin — 5 skills shipped together

Good fit Use it to triage issues, find related open or merged pull requests, close issues that no longer apply, and create one linked pull request for each remaining task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/big-emotion/agent-atelier/issue-train
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.

Any agent
npx skills add big-emotion/agent-atelier --skill issue-train
Clone the repo
git clone --depth 1 https://github.com/big-emotion/agent-atelier

Made for: Claude Code.

Or install pr-trains, the plugin that ships this one along with the rest of its 5 skills.

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 issue-train

README.md
[![agentmods](https://agentmods.dev/badge/skills/big-emotion/agent-atelier/issue-train.svg)](https://agentmods.dev/skills/big-emotion/agent-atelier/issue-train)
Your own site
<a href="https://agentmods.dev/skills/big-emotion/agent-atelier/issue-train"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/issue-train.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,070 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 $0.00057 $0.07070
Opus 5 $0.00028 $0.03535
Sonnet 5 $0.00011 $0.01414
Haiku 4.5 $0.00006 $0.00707

Measured 7d ago against content hash b31e7d6e50cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

issue-train 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 7d 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.

plugins/pr-trains/skills/issue-train/SKILL.md · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Train

Walk a whole list of open GitHub issues in one pass: triage every issue, detect which already have a linked PR (open or merged), detect which were silently fixed by a merged PR that never linked back, close the ones that are no longer pertinent with a stated reason, and for the rest plan + build + open one PR per issue — each PR carrying Closes #<issue-number> in its body so the GitHub UI shows the issue ↔ PR link in the Development field and merging the PR auto-closes the issue.

This is the fourth member of the train family and fills the gap upstream of the others:

  • issue-trainissue → PR (this skill): triages issues, closes stale ones, opens PRs for the rest. Never merges.
  • review-trainreview only: posts reviews + approved / changes-requested labels on PRs. Writes nothing to code.
  • fix-trainfix only: consumes change requests, applies them, pushes. Never merges.
  • merge-trainmerge: orders, fixes CI/conflicts, merges.

The natural pipeline is issue-train → PRs opened → review-trainfix-trainmerge-train → PRs merge → linked issues auto-close.

This skill performs irreversible shared-repo actions (creating branches, pushing, opening PRs, commenting on and closing issues). It follows the same grouped-confirmation model as its siblings: all enumeration, linkage detection, and triage are read-only, one complete plan is presented, and it waits for a single explicit confirmation before any branch push, PR creation, issue comment, or issue close. Until the user confirms, nothing is written anywhere.

When to Activate

  • User shares a GitHub issues URL and asks to process / triage / clear / implement the open issues.
  • User says: "process all the open issues", "go through every open issue and open PRs", "triage the issue backlog", "close the stale issues and implement the rest", "clear the issue queue", "open a PR for every open issue that's still pertinent".
  • User invokes /issue-train (optionally with a GitHub issues URL or --dry-run).

Read the full file on GitHub · 275 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. 7d ago First seen · 275 lines · 57 tokens per session scan A b31e7d6e50cb

Subscribe to this mod's changes

issue-train is a skill published in the GitHub repository big-emotion/agent-atelier (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 7,070 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

bootstrap-working-agreements

Bootstrap a new repo with the full working-agreements + GitHub Project + CLAUDE.md hub-and-spokes setup in one pass. Use on a fresh repo, or on an existing repo that has no .claude/ tooling yet. Calls github-project-setup and split-claudemd as sub-steps; writes .claude/rules/working-agreements.md and a starter root…

toBzh30/Claude-Project-Bootstrap · 98 tokens

merge-review

Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.

SethGammon/Citadel · 40 tokens

catchup

Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.

oliver-kriska/claude-elixir-phoenix · 48 tokens

backlog

Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…

umputun/cc-thingz · 96 tokens

jira

Jira integration — view issues, generate branches, create tickets, transition status. Use when: user mentions Jira ticket key (XX-123), says /jira, wants to create branch from ticket, create a new ticket, or update Jira status. Not for: GitHub issues (use issue-analyze).

sd0xdev/sd0x-harness · 64 tokens

glab

Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line. Use this skill when the user needs to interact with GitLab resources or perform GitLab workflows.

NikiforovAll/claude-code-rules · 59 tokens