parallel-assign

parallel-assign is a skill for Claude Code from happy-nut/claude-plugin-viban. It costs 20 tokens per session (2,285 once invoked), scanned A, original, MIT.

A workflow for assigning several independent backlog issues to separate coding agents using Git worktrees, which keep each change isolated.

In plain words
What is it for?
Use it to pick up multiple independent issues, have agents implement and test them, and resolve their work in parallel.
Why use it?
It avoids making unrelated fixes compete for the same files or branch and coordinates the results in one process.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md; mentions subagents.

Part of the viban plugin — 7 skills, 7 commands, 1 hook shipped together

Good fit Use it to pick up multiple independent issues, have agents implement and test them, and resolve their work in parallel.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/happy-nut/claude-plugin-viban/parallel-assign
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.

Any agent
npx skills add happy-nut/claude-plugin-viban --skill parallel-assign
Clone the repo
git clone --depth 1 https://github.com/happy-nut/claude-plugin-viban

Made for: Claude Code.

Or install viban, the plugin that ships this one along with the rest of its 7 skills, 7 commands, 1 hook.

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-assign

README.md
[![agentmods](https://agentmods.dev/badge/skills/happy-nut/claude-plugin-viban/parallel-assign.svg)](https://agentmods.dev/skills/happy-nut/claude-plugin-viban/parallel-assign)
Your own site
<a href="https://agentmods.dev/skills/happy-nut/claude-plugin-viban/parallel-assign"><img src="https://agentmods.dev/badge/skills/happy-nut/claude-plugin-viban/parallel-assign.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,285 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 $0.00020 $0.02285
Opus 5 $0.00010 $0.01143
Sonnet 5 $0.00004 $0.00457
Haiku 4.5 $0.00002 $0.00229

Measured 7d ago against content hash d4e63890ec25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

parallel-assign 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 7d 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.

skills/parallel-assign/SKILL.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/parallel-assign

Parallel resolution of independent backlog issues via git worktrees.

CLI only (no direct viban.json access) | Opus sub-agents in isolated worktrees

viban is a zsh CLI tool. Always invoke as viban <command>, NEVER as python -m viban or python viban.

Input: $ARGUMENTS (optional: number of issues, default 3)


Output Rules

  • Do NOT output any preamble. No "Your Task:", "I'll now...", "Let me...", or task summaries before starting work.
  • NEVER delegate work back to the user. Each agent must complete its assigned issue fully — writing code, tests, and verifying. Phrases like "Your Task:", "TODO(human)", "Waiting for your implementation", "Take your time", or any message that asks the user to write code are strictly FORBIDDEN. If you encounter a TODO comment, implement it yourself.
  • Start executing Phase 0 immediately and silently.

Phase 0: SETUP

0.1 Read Workflow

[ -f ".viban/workflow.md" ] && cat ".viban/workflow.md"

Fallback to CLAUDE.md, then default. Same as /viban:assign Phase 0.1.

0.2 Parse Arguments

Extract count from $ARGUMENTS:

  • Number provided (e.g. /viban:parallel-assign 5) → use that number
  • No number → default to 3
  • Maximum: 5

0.3 Check Backlog & Git State

viban list

Count available backlog issues. Adjust N down if fewer available. If backlog is empty: notify user and exit.

[ -n "$(git status --porcelain)" ] && echo "Warning: Uncommitted changes"
git checkout main && git fetch origin main && git reset --hard origin/main

0.4 Assign Issues

Assign N issues, each with a unique session ID. Determine branch names per workflow convention:

ISSUES=()  # Array of "ID|BRANCH" pairs
for i in $(seq 1 $N); do
    SESSION=$(echo "${RANDOM}${i}" | md5 | head -c 8)
    ID=$(viban assign "$SESSION" 2>&1 | tail -1)
    [[ -z "$ID" || "$ID" == "No backlog" ]] && break

    BRANCH="issue-${ID}"

    ISSUES+=("${ID}|${BRANCH}")
done

Read the full file on GitHub · 303 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. 7d ago First seen · 303 lines · 20 tokens per session scan A d4e63890ec25

Subscribe to this mod's changes

parallel-assign is a skill published in the GitHub repository happy-nut/claude-plugin-viban (5 stars, last pushed 6mo ago), licensed MIT. It adds 20 tokens to every session and 2,285 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 2026-08-31.