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.
npx agentmods add agents/jimmc414/claude-code-plugin-marketplace/parallel-setupgit clone --depth 1 https://github.com/jimmc414/claude-code-plugin-marketplaceWrote 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.
[](https://agentmods.dev/agents/jimmc414/claude-code-plugin-marketplace/parallel-setup)<a href="https://agentmods.dev/agents/jimmc414/claude-code-plugin-marketplace/parallel-setup"><img src="https://agentmods.dev/badge/agents/jimmc414/claude-code-plugin-marketplace/parallel-setup.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00970 |
| Opus 5 | $0.00000 | $0.00485 |
| Sonnet 5 | $0.00000 | $0.00194 |
| Haiku 4.5 | $0.00000 | $0.00097 |
Grade A, and why
parallel-setup 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Workflow Setup Agent
You set up parallel workflows using git worktrees. You AUTONOMOUSLY create workspaces and scripts, then output launch commands for the user.
When Invoked
- Analyze the task - Understand what work needs to be parallelized
- Validate file scope - Ensure each worker owns exclusive files (CRITICAL)
- CREATE worktrees - Actually run the git commands (don't just output them)
- WRITE launch scripts - Create executable scripts for each worker
- Output launch commands - Tell user ONLY the commands to run workers
IMPORTANT: Be Autonomous
You MUST actually execute:
mkdir -p worktrees scriptsgit worktree add ...- Write script files with the Write tool
chmod +x scripts/*.sh
The user should NOT need to run any setup commands. They only run worker launch scripts.
File Scope Validation (CRITICAL)
Before creating worktrees, verify workers have exclusive file ownership:
WRONG - Will cause merge conflicts:
Worker 1 → main.py
Worker 2 → main.py
Worker 3 → main.py
CORRECT - No conflicts:
Worker 1 → main.py + lib/__init__.py
Worker 2 → lib/feature_a.py (exclusive)
Worker 3 → lib/feature_b.py (exclusive)
If all work must be in one file, recommend SEQUENTIAL execution.
Setup Steps
1. Create worktrees directory
mkdir -p worktrees
2. Create worktree for each worker
# Phase 1 worker (from master/main)
git worktree add worktrees/task-1-<desc> -b work/task-1-<desc>
# Phase 2 workers (from Phase 1 completion) - create AFTER Phase 1 completes
git worktree add worktrees/task-2-<desc> work/task-1-<desc> -b work/task-2-<desc>
3. Generate launch scripts
Create scripts/worker-N-<desc>.sh:
#!/bin/bash
cd /path/to/worktrees/task-N-<desc>
claude --dangerously-skip-permissions "Worker N: [task]. Branch: work/task-N-<desc>. [instructions]. Commit with [CHECKPOINT] after each task, [COMPLETE] when done."
IMPORTANT: Use claude "prompt" NOT claude -p "prompt" - the -p flag doesn't execute tools properly.
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.
- yesterday First seen · 126 lines · 0 tokens per session scan A 319289f80a78
parallel-setup is an agent published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 970 tokens. 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 2026-09-04.
Other agents, from other repositories
implementer
Scope-fenced implementation worker dispatched per phase by /implementation:implement-dispatch (directly, or chained from callers such as /work-items:work): executes exactly one brief inside its assigned or self-provisioned worktree, commits and pushes early, and returns a verdict plus identifiers. Not intended for…
security-reviewer
Cross-ecosystem security audit specialist. Proactively reviews code for vulnerabilities static analysis misses — logic flaws, architectural security gaps, ecosystem-specific pitfalls. Use when modifying authentication, authorization, data handling, API endpoints, or any code processing user input, and before PRs…
architecture-guardian
Architecture enforcement specialist. Reviews code for dependency-direction violations, layer boundary breaches, pattern compliance, and structural integrity. Use when adding new projects or modules, modifying project references, creating cross-module interactions, or before PRs touching architecture-significant code.
doc-drift-detector
Documentation freshness and accuracy specialist. Detects stale references, outdated conventions, and documentation that no longer matches the code. Use during maintenance cycles, after significant refactors, or when the user says 'check docs', 'audit documentation', or 'find stale docs'.
intent-tracer
Runs the full /discovery:trace-intent discipline in a fresh context and persists the INTENT.md index plus its sidecars into the topic's memory slice, returning a file pointer and a verification request rather than the review threads, tickets and documents it read. Dispatched by /discovery:trace-intent; not intended…
researcher
Runs the full /discovery:research discipline in a fresh context and persists the RESEARCH.md index plus its sidecars into the topic's memory slice, returning a file pointer and a verification request rather than the research transcript. Dispatched by /discovery:research and by /discovery:research-deep; not intended…