build-task-grouper

build-task-grouper is an agent for Claude Code from rp1-run/rp1. It costs 17 tokens per session (603 once invoked), scanned A, original, Apache-2.0.

A task-grouping agent turns pending tasks into execution units for a builder-and-reviewer workflow. Simple tasks are batched together, while medium or complex tasks are kept separate.

In plain words
What is it for?
Use it to organise a list of pending tasks before sending them to a build-and-review process, returning the groups as JSON.
Why use it?
It reduces the need to decide manually which tasks should be handled together and which need individual attention.

Agent for Claude Code

Written for Claude Code: arguments in frontmatter. Also seen: model in frontmatter.

Part of the rp1-dev plugin — 23 skills, 36 agents shipped together

Good fit Use it to organise a list of pending tasks before sending them to a build-and-review process, returning the groups as JSON.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rp1-run/rp1/build-task-grouper
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.

Clone the repo
git clone --depth 1 https://github.com/rp1-run/rp1

Made for: Claude Code.

Or install rp1-dev, the plugin that ships this one along with the rest of its 23 skills, 36 agents.

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 build-task-grouper

README.md
[![agentmods](https://agentmods.dev/badge/agents/rp1-run/rp1/build-task-grouper.svg)](https://agentmods.dev/agents/rp1-run/rp1/build-task-grouper)
Your own site
<a href="https://agentmods.dev/agents/rp1-run/rp1/build-task-grouper"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/build-task-grouper.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 603 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 $0.00017 $0.00603
Opus 5 $0.00009 $0.00302
Sonnet 5 $0.00003 $0.00121
Haiku 4.5 $0.00002 $0.00060

Measured 8d ago against content hash 2fcedc2dda43, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

build-task-grouper 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.

plugins/dev/agents/build-task-grouper.md · 101 lines

What it actually says

Build Task Grouper

Groups parsed tasks into execution units for builder-reviewer loop.

CRITICAL: Output ONLY JSON. No tools needed - pure logic agent.

1. Grouping Algorithm

Process only pending tasks from input.

units = []
simple_buffer = []
unit_counter = 1

for task in pending_tasks:
  if task.complexity == "simple":
    simple_buffer.append(task)
    if len(simple_buffer) >= MAX_SIMPLE_BATCH:
      units.append({
        unit_id: unit_counter++,
        task_ids: [t.task_id for t in simple_buffer],
        complexity: "simple"
      })
      simple_buffer = []
  else:
    # Flush simple buffer first
    if simple_buffer:
      units.append({
        unit_id: unit_counter++,
        task_ids: [t.task_id for t in simple_buffer],
        complexity: "simple"
      })
      simple_buffer = []
    # Add complex/medium task isolated
    units.append({
      unit_id: unit_counter++,
      task_ids: [task.task_id],
      complexity: task.complexity
    })

# Flush remaining simple tasks
if simple_buffer:
  units.append({
    unit_id: unit_counter++,
    task_ids: [t.task_id for t in simple_buffer],
    complexity: "simple"
  })

2. Output Contract

Return ONLY this JSON:

{
  "status": "success",
  "task_units": [
    {"unit_id": 1, "task_ids": ["T1", "T2", "T3"], "complexity": "simple"},
    {"unit_id": 2, "task_ids": ["T4"], "complexity": "complex"},
    {"unit_id": 3, "task_ids": ["T5"], "complexity": "medium"}
  ],
  "summary": {
    "total_units": 3,
    "total_tasks": 5,
    "skipped_done": 2,
    "skipped_blocked": 0
  }
}

Fields:

  • task_units: Array of grouped units
  • summary: Counts and skipped tasks

{% include_shared "anti-loop.md" %}

{% include_shared "output-discipline.md" %}

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 · 101 lines · 17 tokens per session scan A 2fcedc2dda43

Subscribe to this mod's changes

build-task-grouper is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed yesterday), licensed Apache-2.0. It adds 17 tokens to every session and 603 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.

Related

Other agents, from other repositories