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 instructions/c9r-io/orchestrator/agents-mdgit clone --depth 1 https://github.com/c9r-io/orchestratorWrote 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.
[](https://agentmods.dev/instructions/c9r-io/orchestrator/agents-md)<a href="https://agentmods.dev/instructions/c9r-io/orchestrator/agents-md"><img src="https://agentmods.dev/badge/instructions/c9r-io/orchestrator/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01468 | $0.01468 |
| Opus 5 | $0.00734 | $0.00734 |
| Sonnet 5 | $0.00294 | $0.00294 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
orchestrator AGENTS.md 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Orchestrator — AI Dev Platform Index
Project Overview
This project is an Agent Orchestrator — a Harness Engineering control plane for agent-first software delivery. It turns shell-native coding agents (Claude Code, OpenCode, Codex, Gemini CLI, etc.) into governed execution units that participate in long-running, multi-step engineering workflows through Kubernetes-style YAML manifests.
Core Capabilities
- Workflow Orchestration: Declarative multi-step workflows with loop control, guard steps, DAG execution, and CEL-based prehooks
- Agent Orchestration: Capability matching, health scoring, rotation, and load balancing across heterogeneous shell agents
- Long-running Automation: Task persistence, event streams, trigger-based task creation (cron/event/webhook), and guarded workflow loops
Architecture
orchestrator (CLI) ──gRPC/UDS──> orchestratord (daemon)
├── gRPC server (tonic)
├── Embedded workers
├── SQLite persistence
└── Sandbox enforcement
Key design principles:
- Capability-driven orchestration: Steps declare required capabilities, agents declare supported capabilities
- Dynamic agent selection: Strategies include CapabilityAware, CostBased, SuccessRateWeighted, PerformanceFirst, Adaptive, LoadBalanced
- Declarative workflow definitions: Steps can be builtin (
init_once,ticket_scan,self_test,self_restart,item_select,loop_guard) or capability-based - CEL prehooks: Conditional step execution via CEL boolean expressions
- Guard steps: Steps that can terminate the workflow loop based on their output
- Dynamic step pools: Runtime step selection based on context and priority
- DAG execution engine: Topological sort, cycle detection, conditional edges
- Built-in observability (structured logs, event streams, task lifecycle tracking)
Manifest Format
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.
- 5d ago First seen · 129 lines · 1,468 tokens per session scan A a15d47f69a43
orchestrator AGENTS.md is an instructions file published in the GitHub repository c9r-io/orchestrator (21 stars, last pushed 3d ago), licensed MIT. It adds 1,468 tokens to every session, about $0.0073 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 instructions, from other repositories
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
ideate AGENTS.md
Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.
omk CLAUDE.md
Claude Code instructions for dmae97/omk, covering claude.md, precedence (read this first), omk runtime map (what you're operating inside), this repo: open-multi-agent-kit / omk monorepo and build / test / check commands.
dakera-rs CLAUDE.md
Claude Code instructions for Dakera-AI/dakera-rs, covering dakera-rs, key commands, architecture and conventions.
icron CLAUDE.md
Instructions for zebbern/icron, covering icron, architecture, key directories, built-in tools and commands.
workstreams disposable.instructions.md
Guidelines for writing code using IDisposable.