execute

A command that executes an existing queue of complete solutions, following their dependency order and running independent solutions in parallel. A DAG is a dependency map showing what must happen before what.

In plain words
What is it for?
Use it to run a selected issue queue, dispatch each solution with all its tasks, and mark solutions complete as execution finishes.
Why use it?
It coordinates multi-solution work in one isolated worktree and prevents completion statuses from being changed inconsistently.

Command for Claude Code

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/catlog22/claude-code-workflow/execute
Clone the repo
git clone --depth 1 https://github.com/catlog22/Claude-Code-Workflow

Made for: Claude Code.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,836 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.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.05836
Opus 5 $0.00008 $0.02918
Sonnet 5 $0.00003 $0.01167
Haiku 4.5 $0.00002 $0.00584

Measured 3d ago against content hash 30fc444c3166, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

execute 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 3d 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/execute.md · 630 lines

How it starts

The opening of the file, as written. The whole thing — 630 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Mode

When --yes or -y: Auto-confirm execution, use recommended settings.

Issue Execute Command (/issue:execute)

Overview

Minimal orchestrator that dispatches solution IDs to executors. Each executor receives a complete solution with all its tasks.

Design Principles:

  • queue dag → returns parallel batches with solution IDs (S-1, S-2, ...)
  • detail <id> → READ-ONLY solution fetch (returns full solution with all tasks)
  • done <id> → update solution completion status
  • No race conditions: status changes only via done
  • Executor handles all tasks within a solution sequentially
  • Single worktree for entire queue: One worktree isolates ALL queue execution from main workspace

Queue ID Requirement (MANDATORY)

Queue ID is REQUIRED. You MUST specify which queue to execute via --queue <queue-id>.

If Queue ID Not Provided

When --queue parameter is missing, you MUST:

  1. List available queues by running:
const result = Bash('ccw issue queue list --brief --json');
const index = JSON.parse(result);
  1. Display available queues to user:
Available Queues:
ID                    Status      Progress    Issues
-----------------------------------------------------------
→ QUE-20251215-001   active      3/10        ISS-001, ISS-002
  QUE-20251210-002   active      0/5         ISS-003
  QUE-20251205-003   completed   8/8         ISS-004
  1. Stop and ask user to specify which queue to execute:
AskUserQuestion({
  questions: [{
    question: "Which queue would you like to execute?",
    header: "Queue",
    multiSelect: false,
    options: index.queues
      .filter(q => q.status === 'active')
      .map(q => ({
        label: q.id,
        description: `${q.status}, ${q.completed_solutions || 0}/${q.total_solutions || 0} completed, Issues: ${q.issue_ids.join(', ')}`
      }))
  }]
})
  1. After user selection, continue execution with the selected queue ID.

DO NOT auto-select queues. Explicit user confirmation is required to prevent accidental execution of wrong queue.

Read the full file on GitHub · 630 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. 3d ago First seen · 630 lines · 16 tokens per session scan A 30fc444c3166

Subscribe to this mod's changes

execute is a command published in the GitHub repository catlog22/Claude-Code-Workflow (2,134 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 5,836 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.