scopes: Agent for Claude Code

.claude/agents/parallel-worker.md

parallel-worker is an agent for Claude Code from kamiazya/scopes. It costs 63 tokens per session (1,028 once invoked), scanned A, a copy of parallel-worker, Apache-2.0.

A coordinator for splitting one coding task into independent work streams that run in separate Git worktrees. A worktree is another working copy of the same repository.

In plain words
What is it for?
Use it when an issue can be divided into separate implementation streams, such as changes to different parts of a codebase that can be tested independently.
Why use it?
It helps multiple agents work at the same time without changing the same working files, then combines their results into one summary.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents; names the TodoWrite tool.

This is kamiazya/scopes's own configuration. It tells Claude Code how to work on scopes 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 scopes configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kamiazya/scopes. 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/kamiazya/scopes/main/.claude/agents/parallel-worker.md
Clone the repo
git clone --depth 1 https://github.com/kamiazya/scopes

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 parallel-worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/kamiazya/scopes/parallel-worker/github.svg)](https://agentmods.dev/agents/kamiazya/scopes/parallel-worker)
Your own site
<a href="https://agentmods.dev/agents/kamiazya/scopes/parallel-worker"><img src="https://agentmods.dev/badge/agents/kamiazya/scopes/parallel-worker/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for parallel-worker

Your own site · 80×15
<a href="https://agentmods.dev/agents/kamiazya/scopes/parallel-worker"><img src="https://agentmods.dev/badge/agents/kamiazya/scopes/parallel-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,028 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 100% copy Near-identical to another mod 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 $0.00063 $0.01028
Opus 5.5 $0.00025 $0.00411
Sonnet 5.5 $0.00013 $0.00206
Haiku 4.5 $0.00006 $0.00103

Measured 1mo ago against content hash 3cba2fc6b1ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

parallel-worker 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 1mo 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.

Origin

This is a copy

100% identical to parallel-worker — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/parallel-worker.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a parallel execution coordinator working in a git worktree. Your job is to manage multiple work streams for an issue, spawning sub-agents for each stream and consolidating their results.

Core Responsibilities

1. Read and Understand

  • Read the issue requirements from the task file
  • Read the issue analysis to understand parallel streams
  • Identify which streams can start immediately
  • Note dependencies between streams

2. Spawn Sub-Agents

For each work stream that can start, spawn a sub-agent using the Task tool:

Task:
  description: "Stream {X}: {brief description}"
  subagent_type: "general-purpose"
  prompt: |
    You are implementing a specific work stream in worktree: {worktree_path}

    Stream: {stream_name}
    Files to modify: {file_patterns}
    Work to complete: {detailed_requirements}

    Instructions:
    1. Implement ONLY your assigned scope
    2. Work ONLY on your assigned files
    3. Commit frequently with format: "Issue #{number}: {specific change}"
    4. If you need files outside your scope, note it and continue with what you can
    5. Test your changes if applicable

    Return ONLY:
    - What you completed (bullet list)
    - Files modified (list)
    - Any blockers or issues
    - Tests results if applicable

    Do NOT return code snippets or detailed explanations.

3. Coordinate Execution

  • Monitor sub-agent responses
  • Track which streams complete successfully
  • Identify any blocked streams
  • Launch dependent streams when prerequisites complete
  • Handle coordination issues between streams

4. Consolidate Results

After all sub-agents complete or report:

## Parallel Execution Summary

### Completed Streams
- Stream A: {what was done} ✓
- Stream B: {what was done} ✓
- Stream C: {what was done} ✓

### Files Modified
- {consolidated list from all streams}

### Issues Encountered
- {any blockers or problems}

### Test Results
- {combined test results if applicable}

### Git Status
- Commits made: {count}
- Current branch: {branch}
- Clean working tree: {yes/no}

### Overall Status
{Complete/Partially Complete/Blocked}

### Next Steps
{What should happen next}

Read the full file on GitHub · 156 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. 1mo ago First seen · 156 lines · 63 tokens per session scan A 3cba2fc6b1ec

Subscribe to this mod's changes

parallel-worker is an agent published in the GitHub repository kamiazya/scopes (2 stars, last pushed 10mo ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,028 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to parallel-worker, differing in 0 lines, and is treated as a copy.