agent-system

A workflow definition that connects multiple language-model agents in a directed graph, so each agent can pass work to another.

In plain words
What is it for?
Use it to coordinate planner, researcher, writer, or other agents and require review before continuing or completing a task.
Why use it?
It makes multi-step agent work explicit, including pipelines, delegation, and human review 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/orlojhq/orloj/agent-system
Clone the repo
git clone --depth 1 https://github.com/OrlojHQ/orloj
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 3,477 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 $0.03477
Opus 5 $0.00000 $0.01739
Sonnet 5 $0.00000 $0.00695
Haiku 4.5 $0.00000 $0.00348

Measured yesterday against content hash 59618bc34309, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-system 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 yesterday.

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.

docs/pages/concepts/agents/agent-system.md · 485 lines

How it starts

The opening of the file, as written. The whole thing — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentSystem

An AgentSystem composes multiple Agents into a directed graph that Orloj executes as a coordinated workflow. The graph defines how messages flow between agents during task execution.

Agent systems can also declare human review checkpoints:

  • spec.graph.<node>.review: review a node's output before downstream routing continues
  • spec.completion_review: review the final task output before the task is marked Succeeded

Defining an AgentSystem

apiVersion: orloj.dev/v1
kind: AgentSystem
metadata:
  name: report-system
  labels:
    orloj.dev/domain: reporting
    orloj.dev/usecase: weekly-report
spec:
  agents:
    - planner-agent
    - research-agent
    - writer-agent
  graph:
    planner-agent:
      next: research-agent
    research-agent:
      next: writer-agent

Graph Topologies

The graph field supports three fundamental patterns:

Pipeline -- sequential stage-by-stage execution where each agent hands off to the next.

graph:
  planner-agent:
    edges:
      - to: research-agent
  research-agent:
    edges:
      - to: writer-agent

Hierarchical -- a manager delegates to leads, who delegate to workers, with a join gate that waits for all branches before proceeding.

graph:
  manager-agent:
    edges:
      - to: research-lead-agent
      - to: social-lead-agent
  research-lead-agent:
    edges:
      - to: research-worker-agent
  social-lead-agent:
    edges:
      - to: social-worker-agent
  research-worker-agent:
    edges:
      - to: editor-agent
  social-worker-agent:
    edges:
      - to: editor-agent
  editor-agent:
    join:
      mode: wait_for_all

Swarm with loop -- parallel scouts report back to a coordinator in iterative cycles, bounded by Task.spec.max_turns.

graph:
  coordinator-agent:
    edges:
      - to: scout-alpha-agent
      - to: scout-beta-agent
      - to: synthesizer-agent
  scout-alpha-agent:
    edges:
      - to: coordinator-agent
  scout-beta-agent:
    edges:
      - to: coordinator-agent

Read the full file on GitHub · 485 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. yesterday First seen · 485 lines · 0 tokens per session scan A 59618bc34309

Subscribe to this mod's changes

agent-system is an agent published in the GitHub repository OrlojHQ/orloj (117 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,477 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 2026-08-30.

Related

Other agents, from other repositories

Explore

Fast read-only codebase & docs exploration. Returns structured findings, never raw file dumps.

BlackBeltTechnology/pi-agent-dashboard · 18 tokens

Audit

Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…

BlackBeltTechnology/pi-agent-dashboard · 98 tokens

harness-radar

Weekly movement briefing on the AI agent harness space — what climbed, what entered the radar, what died — from the best-of-Agent-Harnesses dataset, which rescores itself every week. Use on a schedule (cron, /loop, a routine) or whenever the user asks "what changed in agent land".

RyanAlberts/best-of-Agent-Harnesses · 68 tokens

Executive Scripter

Identify repeated interactive tasks and encode them as committed scripts. Audit scripts/ for gaps, propose new scripts, and extend existing ones — enforcing the programmatic-first principle.

EndogenAI/dogma · 38 tokens

GitHub

Executive-tier agent owning all git and GitHub API write operations — commits, pushes, PR creation, issue updates, label management. Receives approved changes from any executive after Review APPROVED. The sole executor of remote writes in the fleet.

EndogenAI/dogma · 51 tokens

pact-reviewer

Use proactively before committing feature work or multi-file changes (3+ files), or when the main conversation says a task is "done", "finished", "ready to commit", or "looks good". Skip for trivial commits (typo fixes, version bumps, single-line config changes). Runs PACT's governance checklist in an isolated context…

jonathanmr22/pact · 89 tokens