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.
npx agentmods add agents/untra/operator/indexgit clone --depth 1 https://github.com/untra/operatorWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00007 | $0.00580 |
| Opus 5 | $0.00003 | $0.00290 |
| Sonnet 5 | $0.00001 | $0.00116 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
index 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operator orchestrates AI coding agents to work on tickets from your kanban board. The following agents are currently supported:
Available Agents
| Agent | Status | Notes |
|---|---|---|
| Claude | Recommended | Full feature support |
| Codex | Supported | OpenAI's coding model |
| Gemini CLI | Experimental | Google's AI assistant |
Agent Capabilities
Each agent can:
- Read and understand ticket requirements
- Browse project codebases
- Write and modify code
- Run tests and builds
- Create pull requests
Choosing an Agent
Claude is recommended for most users due to its strong code understanding and generation capabilities. See individual agent pages for setup instructions and specific features.
Agent Lifecycle
Operator tracks every agent it launches through these states:
Created -> Running -> Completed
|
v
Awaiting Input
| State | Description |
|---|---|
| Created | Agent initialized, not yet started |
| Running | Actively working on a ticket |
| Awaiting Input | Needs a human response |
| Completed | Work finished successfully |
| Failed | An error occurred |
Autonomous and Paired Modes
Every issue type declares a mode, and that decides how much of your attention
its tickets need:
- Autonomous — launch and monitor. Minimal intervention, and several can run in parallel across different projects.
- Paired — active human participation, with back-and-forth discussion. One at a time, because they compete for the same operator: you.
Mode is a property of the issue type, not of the agent, so a collection decides which of its work types are hands-off. See Workflows.
Sessions
Agent sessions persist under .operator/:
.operator/
├── state.json
├── sessions/
│ ├── agent-123.json
│ └── agent-456.json
└── history.json
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.
- yesterday First seen · 86 lines · 7 tokens per session scan A 5d2c2b96e0b5
index is an agent published in the GitHub repository untra/operator (36 stars, last pushed 4d ago), licensed MIT. It adds 7 tokens to every session and 580 once invoked, about $0.0000 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.
Other agents, from other repositories
code-reviewer
Review PRs against this checklist. Be concise - only comment on actual issues.
code-reviewer
Final ship-time review of an Idea's aggregate code change — the whole feature across all its tasks, not one task. Read-only; posts a VERDICT comment on the Idea. Spawn after the last task of an idea-rooted proposal is verified.
chorus-proposal-reviewer
Review submitted Chorus proposals for quality — check document completeness, task granularity, AC alignment, and cross-task dependencies. Spawn via the blocking subagent tool after choruspmsubmitproposal.
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
chorus
You are the Chorus main agent for Amazon Kiro CLI. You drive the full Chorus AI-DLC (AI Development Life Cycle) workflow — Idea -> Proposal -> Document + Task -> Execute -> Verify -> Done — collaborating with humans and other agents on the Chorus platform via the @chorus MCP server.