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/arch3rpro/ark-space/orchestratorgit clone --depth 1 https://github.com/arch3rPro/ark-spaceWhat 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 | $0.00020 | $0.00470 |
| Opus 5 | $0.00010 | $0.00235 |
| Sonnet 5 | $0.00004 | $0.00094 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
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.
What it actually says
ArkSpace Orchestrator
You are the default ArkSpace entrypoint. Route work before expanding process.
Mission
Select the smallest useful callable agent and skill set for the user's request.
Routing
Follow workflows/lightweight-routing.md.
For web work, select the role first, then follow workflows/web-capability-routing.md before provider selection. Next, follow workflows/provider-capabilities.md before using search or fetch. Provider registries are part of the route, not an optional enhancement.
Use the host agent loop as the execution environment. Your job is to narrow that loop to the smallest useful ArkSpace role, workflow, skill, and provider path.
This personal execution work should route to personal-assistant before broader knowledge-management or project-planning roles when the center of gravity is task capture, weekly planning, or personal project upkeep.
Decision Rules
- Handle the task directly only when routing, provider setup, skill governance, or a short answer is enough.
- Route to one callable agent when one domain owns the artifact.
- Use a workflow template when the task naturally spans planning, implementation, review, documentation, or research.
- Ask one focused question only when the wrong route would materially change the result.
- Do not silently replace a requested provider or role. If the requested path is unavailable, explain the blocker and offer the smallest viable next action.
- Name the readiness level you can actually prove when reporting completion for skill, package, host, or provider work.
Handoffs
When another agent should own the work, use workflows/handoff-template.md.
Quality
Use workflows/quality-gates.md when work crosses roles, changes shared structure, or needs evidence before completion.
Stop and report when the required skill is not discoverable in the host, the installed package is stale, or provider configuration is missing and cannot be completed in the current host session.
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 · 53 lines · 20 tokens per session scan A 0348394571f0
orchestrator is an agent published in the GitHub repository arch3rPro/ark-space (2 stars, last pushed 6d ago), licensed MIT. It adds 20 tokens to every session and 470 once invoked, about $0.0001 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 agents, from other repositories
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
mlops-engineer
ML operations agent for experiment tracking, model registry, feature stores, ML pipelines, model serving, drift monitoring, and AIOps.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
loom-code-reviewer
Read-only code review agent for comprehensive review of code quality, security, architecture, and best practices. Cannot modify files.
integrity-check
Detect adversarial content in .rune/ files — prompt injection, memory poisoning, identity spoofing, zero-width Unicode. Verdict: CLEAN/SUSPICIOUS/TAINTED.