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 skills add strikersam/autonomous-ai-agency --skill orchestrationgit clone --depth 1 https://github.com/strikersam/autonomous-ai-agencyWrote 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/skills/strikersam/autonomous-ai-agency/orchestration)<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/orchestration"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/orchestration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/orchestration"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/orchestration.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00028 | $0.01181 |
| Opus 5 | $0.00014 | $0.00590 |
| Sonnet 5 | $0.00006 | $0.00236 |
| Haiku 4.5 | $0.00003 | $0.00118 |
Grade A, and why
orchestration 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 9d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sol Advisor Orchestration
Act as the architect. Own the user's intent, architecture, route choice, decomposition,
implementation or delegation, parent verification, escalation decisions, and final
acceptance. Selective routing has four exact modes: solo, delegate, audit, and
full. Solo is the default. One auxiliary agent is the default maximum; full is an
explicit broad or high-risk exception.
Read references/role-contracts.md before the first delegation. Use references/operations.md for exact spawn, preflight, runtime-evidence, isolation, and maintainer procedures.
Confirm the primary session
Run the primary Codex session on gpt-5.6-sol with high reasoning. Verify the current model and effort when runtime metadata exposes them. If either differs, tell the user to select Sol / High and stop before delegation. If runtime metadata does not expose them, ask the user to confirm Sol / High and stop until confirmed. A skill cannot change the primary model itself; never assume or claim this prerequisite is satisfied.
Declare the route before task tools
Before the first task tool call, emit one machine-auditable declaration:
SELECTIVE ROUTE
mode: solo | delegate | audit | full
risk: <concise, task-specific rationale>
No task tool call may precede this declaration. Choose solo unless a stated risk
justifies another mode. A later declaration may only escalate the route when newly
observed risk justifies it; never silently downgrade. Record the evidence for an
escalation. Details and the task-scoped preflight matrix are in operations.md.
Preflight selected auxiliaries only
Confirm Sol / High in the primary session. Preflight only an auxiliary selected by the declared route: none for solo; Luna / Max for execution delegation, Terra / High for routine delegation, fresh Sol / High for complex-task audit; and the selected implementer plus fresh Sol reviewer for full. Public metadata for role, model, and effort is authoritative. If it omits a model or effort, use the local inspector only for that omitted field. Missing, conflicting, unavailable, or unobservable evidence stops the affected lane; never silently substitute a role, model, effort, or reviewer.
What ships with it
3 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.
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.
- 9d ago First seen · 109 lines · 28 tokens per session scan A 3b398fd0d1bf
orchestration is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 1,181 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 2026-09-03.
Other skills, from other repositories
assimilate-popular-workflows
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
mcp-app-verification
Comprehensive verification checklists for MCP Apps. Tests with basic-host reference, validates handler-before-connect, text fallback, resource URI linking, single-file bundling, host styling, CSP, and legacy pattern detection.
verification-suite
Plan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation. Provides the structured verification layer ensuring GSD artifacts are well-formed and complete.
guardrails-ai-setup
Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.
mcp-app-scaffolding
Scaffolds MCP App project structure with correct directory layout, dependencies, entry points, and framework-specific templates. Handles React (useApp hook), Vanilla JS, Vue, Svelte, Preact, and Solid.