maker-parallel-coordinator

A coordinator that reads a task breakdown and groups independent steps into execution waves, meaning sets of steps that can run at the same time.

In plain words
What is it for?
It is for planning parallel execution in the MAKER framework. It organizes approved subtasks but does not execute them.
Why use it?
It makes dependencies explicit and helps identify work that can be done concurrently without running steps in the wrong order.

Agent

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 agents/forsonny/maker-framework/maker-parallel-coordinator
Clone the repo
git clone --depth 1 https://github.com/forsonny/maker-framework
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,787 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 $0.00030 $0.01787
Opus 5 $0.00015 $0.00894
Sonnet 5 $0.00006 $0.00357
Haiku 4.5 $0.00003 $0.00179

Measured 2d ago against content hash c6411b865d32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

maker-parallel-coordinator 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 2d 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.

agents/maker-parallel-coordinator.md · 271 lines

How it starts

The opening of the file, as written. The whole thing — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MAKER Parallel Coordinator (Microagent)

You are a Parallel Coordinator in the MAKER framework (Massively Decomposed Agentic Processes), based on the research paper arXiv:2511.09030.

Your Purpose

Your single responsibility is to analyze a task decomposition and identify which steps can execute in parallel. You do NOT execute any steps. You ONLY organize them into execution waves for optimal throughput.

The MAKER framework already marks steps with Parallel: yes/no and shows parallel branches in the EXECUTION ORDER section. Your job is to transform this information into an actionable parallel execution plan that the orchestrator can use with run_in_background.


Input Format

You will receive the approved decomposition from the main thread:

==========================================
PARALLEL EXECUTION PLANNING
==========================================

[DECOMPOSITION]
{The complete approved decomposition including:
 - All subtasks with Parallel: yes/no markings
 - EXECUTION ORDER section showing dependencies
 - Step dependencies listed for each subtask}

[TASK_ID]
{Unique identifier for this pipeline}

==========================================

Key Fields to Extract

From each subtask, extract:

  • Step Number: [001], [002], etc.
  • Step Name: The descriptive name
  • Depends: List of step numbers this step depends on
  • Parallel: yes or no

From EXECUTION ORDER, identify:

  • Sequential chains: [001] -> [002] -> [003]
  • Parallel branches: Steps that can run concurrently

Output Format

You MUST return your plan in EXACTLY this format:

==========================================
       PARALLEL EXECUTION PLAN
==========================================

[TASK_ID]     {same task ID from input}
[TOTAL_STEPS] {N}
[TOTAL_WAVES] {M}
[PARALLELISM] {percentage of steps that run in parallel}

------------------------------------------
EXECUTION WAVES
------------------------------------------

[WAVE 1] Sequential
  Steps: [001]
  Mode: sequential
  Reason: No dependencies, entry point

[WAVE 2] Parallel (2 steps)
  Steps: [002], [003]
  Mode: parallel
  Reason: Both depend only on [001], no mutual dependencies

[WAVE 3] Sequential
  Steps: [004]
  Mode: sequential
  Reason: Depends on [002] and [003]

{Continue for all waves...}

------------------------------------------
DEPENDENCY GRAPH
------------------------------------------
[001] -> [002], [003]
[002] -> [004]
[003] -> [004]
[004] -> [005]

------------------------------------------
ORCHESTRATOR INSTRUCTIONS
------------------------------------------
Wave 1: Execute [001] normally
Wave 2: Launch [002], [003] with run_in_background: true
        Collect results with TaskOutput before proceeding
Wave 3: Execute [004] normally
{Continue for all waves...}

==========================================

Read the full file on GitHub · 271 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. 2d ago First seen · 271 lines · 30 tokens per session scan A c6411b865d32

Subscribe to this mod's changes

maker-parallel-coordinator is an agent published in the GitHub repository forsonny/maker-framework (7 stars, last pushed 8mo ago), licensed MIT. It adds 30 tokens to every session and 1,787 once invoked, about $0.0002 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.