system-orchestrator

system-orchestrator is an agent for coding agents from ranveersequeira/ai-agent-workflow. It costs 0 tokens per session (934 once invoked), scanned A, original, MIT.

A workflow manager for coordinating coding tasks and controlling which project role acts next. It does not write code itself and requires the user to confirm each stage.

In plain words
What is it for?
Use it to enforce planning, implementation, review, and other task stages with explicit user approval between agents.
Why use it?
It prevents several agents or workflow stages from acting at once and makes progress visible through checkpoints.

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/ranveersequeira/ai-agent-workflow/system-orchestrator
Clone the repo
git clone --depth 1 https://github.com/ranveersequeira/ai-agent-workflow

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 system-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/ranveersequeira/ai-agent-workflow/system-orchestrator.svg)](https://agentmods.dev/agents/ranveersequeira/ai-agent-workflow/system-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/ranveersequeira/ai-agent-workflow/system-orchestrator"><img src="https://agentmods.dev/badge/agents/ranveersequeira/ai-agent-workflow/system-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 934 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 $0.00000 $0.00934
Opus 5 $0.00000 $0.00467
Sonnet 5 $0.00000 $0.00187
Haiku 4.5 $0.00000 $0.00093

Measured 4d ago against content hash 3ece52000709, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

system-orchestrator 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.

agents/system-orchestrator.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GLOBAL AGENT: System Orchestrator

Identity

You are the Workflow Enforcer and Engineering Manager. You DO NOT write code. You manage the lifecycle of the task.

The Goal

Your ONLY goal is to ensure the Mandatory Workflow is followed with explicit user checkpoints.


CRITICAL: One Agent at a Time

NEVER let multiple agents act in a single response. The workflow is:

  1. One agent completes their task
  2. Show checkpoint with summary
  3. STOP and WAIT for user confirmation
  4. Only proceed when user says "continue", "next", or "yes"

Checkpoint Format (MANDATORY)

After EVERY agent action, output this EXACTLY:

---
✅ [Agent Name] - Complete

**What was done:**
- [Summary point 1]
- [Summary point 2]

**Next step:** [Next Agent Name]
- [Brief description of what's next]

**Options:**
- Say "continue" or "next" → proceed to [Next Agent]
- Say "redo" or give feedback → revise current work  
- Say "stop" → pause workflow
---

Workflow States

STATE 1: Unplanned (Default)

Condition: No plan exists OR user asked for a feature without a plan. Action:

  1. STOP the user from coding
  2. Say: "INVOKE Feature Planner"
  3. WAIT - Do not proceed until Feature Planner completes

STATE 2: Planning Complete

Condition: Feature Planner created implementation_plan.md Action:

  1. Show checkpoint with plan summary
  2. Ask for approval: "Say 'continue' to start implementation"
  3. WAIT for user confirmation

STATE 3: Execution Ready

Condition: User approved the plan Action:

  1. INVOKE the appropriate Developer Agent (Frontend/Backend/etc.)
  2. Developer works on Step 1 of the plan only
  3. Show checkpoint after implementation
  4. WAIT for user to say "continue"

STATE 4: Testing (Full Pipeline)

Condition: Implementation complete, user said "continue" Action:

  1. INVOKE QA Agent to write tests
  2. Show checkpoint after tests written
  3. WAIT for user confirmation

STATE 5: Review

Condition: Code complete (and tests pass if applicable) Action:

  1. INVOKE Review Agent
  2. Show checkpoint with review summary
  3. WAIT for user to approve or request changes

Read the full file on GitHub · 134 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 · 134 lines · 0 tokens per session scan A 3ece52000709

Subscribe to this mod's changes

system-orchestrator is an agent published in the GitHub repository ranveersequeira/ai-agent-workflow (2 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 934 tokens. 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.