claude-pipeline: Skill for Claude Code

.claude/skills/handle-issues/SKILL.md

handle-issues is a skill for Claude Code from aaddrick/claude-pipeline. It costs 23 tokens per session (4,171 once invoked), scanned A, original, MIT.

An automated workflow for processing multiple GitHub issues through a batch orchestrator. It supports rate-limit handling, progress tracking, and resuming a paused session.

In plain words
What is it for?
Use it to process issues selected by a query, such as assigned issues, critical bugs, milestone work, or a specified range, with suitable specialist agents.
Why use it?
It removes the need to run and monitor each matching issue separately, especially when many issues share a selection rule.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool; positional $N argument; mentions Claude Code.

This is aaddrick/claude-pipeline's own configuration. It tells Claude Code how to work on claude-pipeline itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-pipeline configures →

Reuse

Borrowing it

Nothing to install: this file belongs to aaddrick/claude-pipeline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aaddrick/claude-pipeline/main/.claude/skills/handle-issues/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aaddrick/claude-pipeline

Made for: Claude Code.

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 handle-issues

README.md
[![agentmods](https://agentmods.dev/badge/skills/aaddrick/claude-pipeline/handle-issues.svg)](https://agentmods.dev/skills/aaddrick/claude-pipeline/handle-issues)
Your own site
<a href="https://agentmods.dev/skills/aaddrick/claude-pipeline/handle-issues"><img src="https://agentmods.dev/badge/skills/aaddrick/claude-pipeline/handle-issues.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,171 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 $0.00023 $0.04171
Opus 5 $0.00012 $0.02086
Sonnet 5 $0.00005 $0.00834
Haiku 4.5 $0.00002 $0.00417

Measured 8d ago against content hash 0f00399ea184, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

handle-issues 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 8d 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/skills/handle-issues/SKILL.md · 489 lines

How it starts

The opening of the file, as written. The whole thing — 489 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handle Issues

Batch process multiple GitHub issues by launching batch-orchestrator.sh which handles the execution loop, rate limits, and status tracking autonomously. This skill focuses on setup and monitoring.

Announce at start: "Using handle-issues to batch process issues. Query: $CONTEXT"

Arguments:

  • $1 — Context query describing which issues to process and how (required)

Examples:

  • /handle-issues "issues assigned to @me ordered by priority"
  • /handle-issues "all open bugs labeled 'critical'"
  • /handle-issues "issues in milestone v2.0 by creation date"
  • /handle-issues "Tailwind removal issues 306-308" (frontend work)

Agent Selection

The orchestrator uses specialized agents via --agent flag to ensure the right expertise for each stage:

Stage Agent Purpose
implement-issue bulletproof-frontend-developer CSS, HTML, Blade templates, frontend styling
implement-issue laravel-backend-developer PHP, Laravel, controllers, services, models
implement-issue (default) General implementation
process-pr code-reviewer Always - reviews PR for quality and standards

Determine agent based on issue content:

  • Frontend issues (CSS, Tailwind, styling, UI, HTML, Blade): Use bulletproof-frontend-developer
  • Backend issues (PHP, Laravel, API, database, auth): Use laravel-backend-developer
  • Mixed or unclear: Use default (no agent specified)

Ask user during confirmation which agent to use if issue type is ambiguous.

Architecture

┌─────────────────────────────────────────────────────────────────┐
│ handle-issues (this skill)                                      │
│  • Gathers issues via gh CLI                                    │
│  • Determines appropriate agent for issue type                  │
│  • Confirms with user (ONLY interaction point)                  │
│  • Writes manifest.json (includes agent)                        │
│  • Launches batch-orchestrator.sh (background)                  │
│  • Reads status.json every 5 minutes                            │
│  • Outputs summary when complete                                │
└─────────────────────────────────────────────────────────────────┘
                              │
                              ▼
┌─────────────────────────────────────────────────────────────────┐
│ batch-orchestrator.sh (shell script)                            │
│  • Loops through issues autonomously                            │
│  • Invokes claude with --agent and --dangerously-skip-permissions│
│  • Parses structured_output via jq                              │
│  • Updates status.json after each operation                     │
│  • Handles rate limits, timeouts, circuit breaker               │
└─────────────────────────────────────────────────────────────────┘

Claude CLI invocations:
  claude -p "/implement-issue #N branch" \
    --agent <frontend|backend> \
    --dangerously-skip-permissions \
    --output-format json \
    --json-schema implement-issue.json

  claude -p "/process-pr #PR #issue branch" \
    --agent code-reviewer \
    --dangerously-skip-permissions \
    --output-format json \
    --json-schema process-pr.json

Read the full file on GitHub · 489 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. 8d ago First seen · 489 lines · 23 tokens per session scan A 0f00399ea184

Subscribe to this mod's changes

handle-issues is a skill published in the GitHub repository aaddrick/claude-pipeline (128 stars, last pushed 6mo ago), licensed MIT. It adds 23 tokens to every session and 4,171 once invoked, about $0.0001 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 2026-08-30.