harness-parallel-coordinator

harness-parallel-coordinator is an agent for coding agents from Intense-Visions/harness-engineering. It costs 37 tokens per session (3,105 once invoked), scanned A, original, MIT.

A coordinator that sends independent coding tasks to separate agents so they can be worked on at the same time, then combines and validates their results.

In plain words
What is it for?
Use it for three or more genuinely independent implementation tasks or whenever a plan includes a parallel work phase. Each task is given its own isolated work area before the results are combined.
Why use it?
It reduces waiting when a larger plan contains tasks that do not depend on one another, while checking for conflicts before the work is integrated.

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/intense-visions/harness-engineering/harness-parallel-coordinator
Clone the repo
git clone --depth 1 https://github.com/Intense-Visions/harness-engineering

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 harness-parallel-coordinator

README.md
[![agentmods](https://agentmods.dev/badge/agents/intense-visions/harness-engineering/harness-parallel-coordinator.svg)](https://agentmods.dev/agents/intense-visions/harness-engineering/harness-parallel-coordinator)
Your own site
<a href="https://agentmods.dev/agents/intense-visions/harness-engineering/harness-parallel-coordinator"><img src="https://agentmods.dev/badge/agents/intense-visions/harness-engineering/harness-parallel-coordinator.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,105 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 $0.00037 $0.03105
Opus 5 $0.00018 $0.01553
Sonnet 5 $0.00007 $0.00621
Haiku 4.5 $0.00004 $0.00311

Measured 4d ago against content hash 65e7478ce846, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

harness-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 4d 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.

.antigravity-extension/agents/harness-parallel-coordinator.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Verify task independence, create focused agent briefs, dispatch Task Executor instances in isolated worktrees, integrate results, and run full validation after all agents complete.

Skills

  • harness-parallel-agents

Steps

  1. Run harness validate (always)
  2. Execute harness-parallel-agents skill (manual)

Methodology

Harness Parallel Agents

Dispatch independent tasks to concurrent agents, integrate results, and verify no conflicts. Only for truly independent problems.

Invoked automatically by harness-autopilot (and standalone harness-execution), not only manually. When a plan's phase has an auto-dispatch wave, the execution loop calls this skill to run that wave. In that mode the caller supplies worktree-per-unit isolation per docs/guides/agent-worktree-patterns.md (one worktree per task, sequential commits, squash-merge on integrate) and has already verified independence via plan_parallelization; this skill still owns the focused agent briefs (Step 2), concurrent dispatch (Step 3), and integration/verification (Steps 4–5). Manual invocation (a human asking to "work in parallel") continues to work unchanged.

When to Use

  • When 3 or more tasks are truly independent (no shared state, no shared files, different subsystems)
  • When tasks involve investigation or implementation in separate parts of the codebase
  • When parallel execution would meaningfully reduce wall-clock time
  • When a plan has tasks explicitly marked as parallelizable
  • When harness-autopilot/harness-execution reaches an auto-dispatch (or confirmed) wave from plan_parallelization — this skill is the wave's dispatcher
  • NOT when failures across tasks might be related (investigate serially to find the common cause)
  • NOT when tasks need full system understanding to complete correctly
  • NOT when agents would modify the same files or shared state
  • NOT when there are fewer than 3 independent tasks (overhead of coordination outweighs parallelism)
  • NOT when the tasks are sequential by nature (each depends on the previous)

Read the full file on GitHub · 299 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. 4d ago First seen · 299 lines · 37 tokens per session scan A 65e7478ce846

Subscribe to this mod's changes

harness-parallel-coordinator is an agent published in the GitHub repository Intense-Visions/harness-engineering (20 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 3,105 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 2026-08-30.