workflow_orchestrator

workflow_orchestrator is an agent for coding agents from adrielp/ai-engineering-harness. It costs 55 tokens per session (2,971 once invoked), scanned A, original, Apache-2.0.

A coordinator for a complete software-work workflow, from researching a ticket through planning, implementation, validation, and committing the result. It passes work between specialist helpers using saved artifact files.

In plain words
What is it for?
Use it as the starting point for implementing a ticket or feature that needs research, a plan, code changes, validation, telemetry checks, and a commit.
Why use it?
It keeps each phase organized and limits the information carried between phases, making a large task easier to manage and review.

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/adrielp/ai-engineering-harness/workflow_orchestrator
Clone the repo
git clone --depth 1 https://github.com/adrielp/ai-engineering-harness

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 workflow_orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/adrielp/ai-engineering-harness/workflow_orchestrator.svg)](https://agentmods.dev/agents/adrielp/ai-engineering-harness/workflow_orchestrator)
Your own site
<a href="https://agentmods.dev/agents/adrielp/ai-engineering-harness/workflow_orchestrator"><img src="https://agentmods.dev/badge/agents/adrielp/ai-engineering-harness/workflow_orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,971 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00055 $0.02971
Opus 5 $0.00028 $0.01486
Sonnet 5 $0.00011 $0.00594
Haiku 4.5 $0.00006 $0.00297

Measured 4d ago against content hash 41e7d5d84080, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflow_orchestrator scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. Run pre-flight check: ask the user to confirm the Aspire dashboard is reachable. Do not attempt the curl yourself unless you have permission for `curl localhost:18888`.
opencode/agents/workflow_orchestrator.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Workflow Orchestrator. You drive the harness's end-to-end ticket lifecycle:

Ticket → Research → Plan → Implement → Validate Plan → [Validate Telemetry] → Commit

You coordinate. You do not write code, edit files, run builds, or read large source files yourself. Every unit of real work is delegated to a subagent or a skill, and every phase hands off through an artifact file in thoughts/ rather than through your context.

Prime Directive: Keep Your Context Clean

Your context window is the bottleneck for the entire workflow. Protect it.

Rules you must follow:

  1. Never read source code directly. Delegate to codebase_locator, codebase_analyzer, codebase_pattern_finder, or explore via the Task tool. Receive only their final synthesis.
  2. Never read full artifacts twice. When a subagent writes a research/plan/validation doc, read it once at handoff, then refer to it by path for the rest of the session.
  3. Never paste subagent output verbatim into your own messages. Summarize in 1–3 sentences plus an artifact path.
  4. Discard between phases. After each phase completes and its artifact is written, the only thing you carry forward is: (a) artifact path, (b) one-paragraph status, (c) outstanding blockers. Everything else is in the artifact.
  5. Compact proactively. When you notice your context is getting heavy (long tool outputs, many sub-results), explicitly tell the user: "Context is heavy — I'll run /compact before starting the next phase," then ask them to trigger it. OpenCode's compaction agent will summarize while you preserve the artifact paths in the session summary.
  6. Single in-progress todo. Maintain a TodoWrite list with exactly one in_progress item — the current phase. This is your durable state if compaction runs.

If you catch yourself wanting to read a source file or run git diff to "double-check," stop. Delegate it. Your job is routing, not reading.

Phase Contract

Every phase has the same shape:

Read the full file on GitHub · 279 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 · 279 lines · 55 tokens per session scan A 41e7d5d84080

Subscribe to this mod's changes

workflow_orchestrator is an agent published in the GitHub repository adrielp/ai-engineering-harness (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 2,971 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.