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 skills/ssheleg/agent-stack/agent-orchestratornpx skills add ssheleg/agent-stack --skill agent-orchestratorgit clone --depth 1 https://github.com/ssheleg/agent-stackWhat 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 | $0.00244 | $0.04573 |
| Opus 5 | $0.00122 | $0.02286 |
| Sonnet 5 | $0.00049 | $0.00915 |
| Haiku 4.5 | $0.00024 | $0.00457 |
Grade A, and why
agent-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 2d 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 — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Orchestrator — Production Best Practices
Patterns from a production multi-agent system. The body is decisions; the mechanisms are one file away, and it is held under a 4750-token budget — a body that grows absorbs the layer that should have been split, and this one did until 2026-08-16.
Architecture Overview
User Question
↓
OrchestratorAgent.run(AgentContext)
├─ Shape check → one loop, or a planned path (§5, references/pipeline.md)
├─ Context loading (a parallel layer: staleness, sources, KB — §13)
├─ History trimming, then context budget allocation
├─ System prompt built from the live capabilities (§10)
└─ Execute:
├─ SIMPLE: LLM → tools → sub-agents → results → LLM → … → answer (§2)
└─ PLANNED: plan → dependency layers → checker → checkpoints → done (§5)
1. The Orchestrator Pattern
Shared Context Object
Pass a single immutable-ish context object to all sub-agents:
@dataclass
class AgentContext:
project_id: str
user_question: str
chat_history: list[Message]
llm_router: LLMRouter # provider abstraction with retry/fallback
tracker: WorkflowTracker # SSE event emitter for real-time UI
workflow_id: str # unique ID for this request
connection_config: ... | None # external resource config
user_id: str | None
preferred_provider: str | None # e.g. "openrouter"
model: str | None # e.g. "<provider>/<model-id>"
extra: dict[str, Any] # pipeline_action, flags, overrides
Key principles:
- Sub-agents never modify context — they return typed results
- Provider/model preferences flow down from user → project defaults → app defaults
extradict carries pipeline state, flags like_skip_complexity, session IDs
Sub-Agent Protocol
Every sub-agent extends a base class:
class BaseAgent(ABC):
@abstractmethod
async def run(self, context: AgentContext, **kwargs) -> AgentResult: ...
@property
@abstractmethod
def name(self) -> str: ...
@staticmethod
def accum_usage(total, usage): ... # merge token counters
What ships with it
11 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.
- references/context-engineering.md 11 KB
- references/governance.md 7.0 KB
- references/graph-engineering.md 24 KB
- references/llm-proxy-billing.md 10 KB
- references/memory-architecture.md 20 KB
- references/memory-landscape.md 8.1 KB
- references/memory-lifecycle.md 9.3 KB
- references/patterns.md 19 KB
- references/pipeline.md 4.4 KB
- references/provider-lifecycle.md 8.8 KB
- references/runtime.md 8.8 KB
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.
- 2d ago First seen · 390 lines · 244 tokens per session scan A eb2ce6b3e991
agent-orchestrator is a skill published in the GitHub repository ssheleg/agent-stack (2 stars, last pushed 2d ago), licensed MIT. It adds 244 tokens to every session and 4,573 once invoked, about $0.0012 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 2026-08-31.
Other skills, from other repositories
cotal-setup
Set up Cotal on this machine: install it, start a local agent mesh (NATS + JetStream), verify it, and put an agent on it. Use when asked to install Cotal, join a Cotal mesh, or let coding agents coordinate as peers.
team-topology
Define a multi-agent team for ANY task on ANY system as an explicit deployment topology - pick the shape from the task's dominant risk, specify the runtime/communication/trust layers, place model capability by lane, present it as a diagram + table + trust-boundary note + open choices, and deploy ONLY after the user…
deploy-agent
Deploy Bindu agents to various environments with safety checks and verification.
add-example-agent
Add a new self-contained example agent under examples/. Use when asked to "create an example for ", "add a tutorial agent", "demo integration with ", or when showcasing a new pattern users should copy.
Skill Creation
Create, structure, and publish skills through the skill-plugin-marketplace pipeline.
demonstrate_governance
Drive every stage of the governance pipeline end to end, then prove that each decision was audited. This is the guided tour of the enforcement spine: the same four stages run on every tool call in the workspace.