ai-issue-loop

ai-issue-loop is a skill for Claude Code from rtorcato/repo-tooling. It costs 173 tokens per session (25,173 once invoked), scanned B, original, MIT.

An automated workflow that processes GitHub issues through coding, review, and pull-request stages. It uses labels to record progress, so it can resume after a crash or restart.

In plain words
What is it for?
Use it to pick up ready issues, run fix rounds, handle Dependabot pull requests, request human merging, and clean up finished or stalled work.
Why use it?
It removes the need to move each issue manually through worktrees, reviews, cleanup, and merge decisions.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Not installable on its own: it reads a path above its own folder, which only exists inside its repository. The line is same repo at ../js-common-worktrees/issue-76 → biome: Checked 141 files.

Part of the repo-tooling plugin — 7 skills shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add rtorcato/repo-tooling
Claude Code
/plugin install repo-tooling

Made for: Claude Code.

Or install repo-tooling, the plugin that ships this one along with the rest of its 7 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 ai-issue-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/rtorcato/repo-tooling/ai-issue-loop.svg)](https://agentmods.dev/skills/rtorcato/repo-tooling/ai-issue-loop)
Your own site
<a href="https://agentmods.dev/skills/rtorcato/repo-tooling/ai-issue-loop"><img src="https://agentmods.dev/badge/skills/rtorcato/repo-tooling/ai-issue-loop.svg" alt="Measured on agentmods" height="20"></a>
Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 25,173 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 5.1 $0.00173 $0.25173
Opus 5 $0.00086 $0.12587
Sonnet 5 $0.00035 $0.05035
Haiku 4.5 $0.00017 $0.02517

Measured 5d ago against content hash 96ace1a438cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

ai-issue-loop scanned grade B with 1 finding 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 5d 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.

grep -qxF '.claude/ai-loop-status' .gitignore || echo '.claude/ai-loop-status' >> .gitignore
skills/ai-issue-loop/SKILL.md · 1,751 lines

How it starts

The opening of the file, as written. The whole thing — 1,751 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ai-issue-loop

One tick of an unattended pipeline: ai-ready issue → worktree → PR → two agent reviews → assigned to you to merge → worktree removed on the next tick. Only Dependabot PRs merge themselves, plus — on a repo whose release environment requires reviewers — a fully-passed issue PR. See Pass 1. Whenever the loop declines to merge, it says why in a comment on the PR.

All state lives in GitHub labels. A tick is a stateless, idempotent pass over that state, so a missed tick, a crash, or a restart costs nothing. Never keep pipeline state in the conversation.

The one constraint that shapes everything

Every agent here authenticates as the user's own gh — no PATs, no bot accounts. GitHub refuses gh pr review --approve on your own PR, so a real GitHub approval is impossible. Approval is therefore a label, and the repo's required status checks stay the real merge gate.

Never run gh pr review --approve. Never set required_pull_request_reviews on the protected branch — it would deadlock every PR.

If you ever switch to real approvals — a second GitHub account reviewing as someone else, so --approve works and the ai-ok-* labels become unnecessary — first check what else writes your branch protection. Any repo-settings tool that treats required_pull_request_reviews as drift will PUT it back to null on its next run, because required review deadlocks solo Dependabot auto-merge. Your approval rule vanishes, merges hand themselves back to the labels, and nothing in that tool's output ties the change to this pipeline. @rtorcato/repo-tooling, which ships this skill, is one such tool — its repo-settings standard asserts required_pull_request_reviews: null, so change that standard before you rely on real approvals.

The same constraint makes everything an agent posts look hand-written by the owner. So every comment any agent leaves — review, blocked, gave-up, declined — opens with a 🤖 *Automated …* italic header line naming which agent wrote it, then a blank line. Name the agent and stop there: a detailed security review under a human's avatar misrepresents who reviewed the code, but why it wears that avatar is read once and then reread on every comment forever.

Read the full file on GitHub · 1,751 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. 5d ago First seen · 1,751 lines · 173 tokens per session scan B 96ace1a438cd

Subscribe to this mod's changes

ai-issue-loop is a skill published in the GitHub repository rtorcato/repo-tooling (2 stars, last pushed 5d ago), licensed MIT. It adds 173 tokens to every session and 25,173 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens