project-orchestration

project-orchestration is a skill for Claude Code, Codex from darrenhinde/OpenAgentsControl. It costs 25 tokens per session (2,445 once invoked), scanned A, original, MIT.

A workflow coordinator for software feature development that divides work among multiple AI agents and passes the needed context between them. It supports lightweight handoffs, interactive planning sessions, and an eight-stage delivery process.

In plain words
What is it for?
Use it to create planning context, collect agent outputs, review sessions, and manage feature work through its staged delivery workflow.
Why use it?
It reduces lost context and unclear ownership when several agents work on one feature. It also keeps planning progress and stage status organized.

Skill for Claude CodeCodex

About the project

OpenAgents Control is a framework that adds plan-first, approval-based coding workflows to OpenCode, an AI coding framework. Developers and teams use it to make agents follow shared coding patterns, work across several programming languages, and validate changes through testing and review. The catalogue includes its agents, skills, commands, plugin, and hook.

darrenhinde/OpenAgentsControl · 4,823 stars · on GitHub

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 skills/darrenhinde/openagentscontrol/project-orchestration
Any agent
npx skills add darrenhinde/OpenAgentsControl --skill project-orchestration
Clone the repo
git clone --depth 1 https://github.com/darrenhinde/OpenAgentsControl

Made for: Claude Code, Codex.

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 project-orchestration

README.md
[![agentmods](https://agentmods.dev/badge/skills/darrenhinde/openagentscontrol/project-orchestration.svg)](https://agentmods.dev/skills/darrenhinde/openagentscontrol/project-orchestration)
Your own site
<a href="https://agentmods.dev/skills/darrenhinde/openagentscontrol/project-orchestration"><img src="https://agentmods.dev/badge/skills/darrenhinde/openagentscontrol/project-orchestration.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,445 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 5.1 $0.00025 $0.02445
Opus 5 $0.00013 $0.01222
Sonnet 5 $0.00005 $0.00489
Haiku 4.5 $0.00003 $0.00245

Measured 6d ago against content hash e214bc14fca7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

project-orchestration 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 6d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (router.sh, scripts/context-index.ts, scripts/session-context-manager.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.opencode/skill/project-orchestration/SKILL.md · 324 lines

How it starts

The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Orchestration Skill

Purpose: Orchestrate multi-agent workflows for feature development

What I Do

Coordinate multi-agent planning and execution workflows:

  • Pass minimal context between planning agents
  • Track planning agent outputs
  • Manage 8-stage feature delivery workflow
  • Maintain planning session state

Three Workflows

1. Context Handoff (Lightweight)

Pass minimal context between agents (RECOMMENDED for automation)

  • Commands: create, get-context, add-output, show
  • Use when: Orchestrating planning agents
  • See: workflows/context-handoff.md

2. Session Context (Interactive)

Human-readable planning narrative (for debugging/review)

  • Commands: session-create, session-load, session-summary
  • Use when: Debugging or reviewing planning sessions
  • See: workflows/context-handoff.md

3. Multi-Stage Delivery (8 Stages)

Full feature delivery workflow

  • Commands: stage-init, stage-status, stage-complete, stage-rollback
  • Use when: Running complete 8-stage feature workflow
  • See: workflows/8-stage-delivery.md

Quick Start

Context Handoff Workflow

# Create context index
bash .opencode/skill/project-orchestration/router.sh create auth-system

# Get minimal context for specific agent
bash .opencode/skill/project-orchestration/router.sh get-context auth-system StoryMapper

# Track agent output
bash .opencode/skill/project-orchestration/router.sh add-output auth-system ArchitectureAnalyzer .tmp/architecture/auth-system/contexts.json

# Show full index
bash .opencode/skill/project-orchestration/router.sh show auth-system

8-Stage Workflow

# Initialize workflow
bash .opencode/skill/project-orchestration/router.sh stage-init auth-system

# Check status
bash .opencode/skill/project-orchestration/router.sh stage-status auth-system

# Mark stage complete
bash .opencode/skill/project-orchestration/router.sh stage-complete auth-system 1

# Rollback if needed
bash .opencode/skill/project-orchestration/router.sh stage-rollback auth-system 1

Read the full file on GitHub · 324 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 324 lines · 25 tokens per session scan A e214bc14fca7

Subscribe to this mod's changes

project-orchestration is a skill published in the GitHub repository darrenhinde/OpenAgentsControl (4,823 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 2,445 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.