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/igovet/codex-cortex-orchestrator/orchestratornpx skills add igovet/codex-cortex-orchestrator --skill orchestratorgit clone --depth 1 https://github.com/igovet/codex-cortex-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/skills/igovet/codex-cortex-orchestrator/orchestrator)<a href="https://agentmods.dev/skills/igovet/codex-cortex-orchestrator/orchestrator"><img src="https://agentmods.dev/badge/skills/igovet/codex-cortex-orchestrator/orchestrator.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 5.1 | $0.00120 | $0.05968 |
| Opus 5 | $0.00060 | $0.02984 |
| Sonnet 5 | $0.00024 | $0.01194 |
| Haiku 4.5 | $0.00012 | $0.00597 |
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 today.
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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cortex Orchestrator v1.15.0
Activation and language
Activate only when the user explicitly selects cortex:orchestrator. help is read-only guidance, harvest and harvest-refresh are explicit knowledge routes, and normal leaves Cortex. Never infer activation from complexity or repository state. The live MCP catalogue is authoritative for every call shape; do not teach or guess arguments outside its schemas.
The host supplies this complete skill content when it activates the route.
Treat that context as the authoritative initial read. After compaction/reset,
SessionStart(source=compact) repeats the exact packaged skill through host context with no
context truncation; the standard host skill loader may also repeat the same
exact load whenever needed. Repetition is never forbidden or consumed. Never
replace either load with cat, shell/filesystem inspection, an MCP resource,
project copy, elevated execution, or a user approval question. If exact host
reload is unavailable, stop before further project operations and report
activation recovery as unavailable.
Worker communication, commentary, reports, and durable ledger prose are English. Coordinator communication follows the latest meaningful user-message language unless explicitly overridden. Preserve exact source text only in schema fields intended for it.
First boundary
For project work, the first execution operation is open_task. Before it, compose the complete semantic outcomes, acceptance conditions, constraints, language, and bounded context without project inspection or task-specific user commentary. Make exactly one complete direct Cortex call: never place task opening inside programmatic tool calling, exec, a batch, parallel calls, or speculative partial calls. Success establishes the sole coordinator identifier, task_ref; retain exactly that value. After an ambiguous transport, retry the identical direct call so the server can reconcile it. Never create a replacement task. If no task can be opened, stop the Cortex route honestly.
What ships with it
1 file 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.
- today Changed · -777 lines · +5 tokens per session 3a82bbee6dce
- 5d ago First seen · 968 lines · 115 tokens per session scan A 7b2749e6f433
orchestrator is a skill published in the GitHub repository igovet/codex-cortex-orchestrator (1 stars, last pushed yesterday), licensed MIT. It adds 120 tokens to every session and 5,968 once invoked, about $0.0006 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
bug-triage
Triage bugs reported in chat/issues, search for duplicates, file or update GitHub issues with full context, and push fix PRs.
ao-desktop-dev
Launch, restart, or troubleshoot the real AO Electron desktop app from this repository; run a checkout against isolated or real local AO data; combine PR branches for local UI review; and diagnose stale Electron processes, port conflicts, or preload bridge mismatches. Use whenever asked to run, open, show, or visually…
using-ao
Catalog of the AO (Agent Orchestrator) ao CLI: spawning workers, managing sessions and projects, sending messages, controlling the shared browser, previewing pages, and daemon control. Use when using the ao CLI, spawning workers, or managing AO sessions in an AO workspace.
summon
Autonomous orchestrator for manifest work items through the development lifecycle. Use when running egregore to process a backlog automatically.
model-router
当需要调度不同模型执行子任务时使用。根据任务类型匹配模型能力，自动选择最优模型并生成调用指令。TRIGGER: 模型调度、model dispatch、选模型、分派任务、多模型协作、路由到模型.
dev-flow
Assess bounded Codex software development requests before choosing direct work or Dev Flow, then provision confirmed Dev Flow Tasks in dedicated Git worktrees. It may be selected implicitly or explicitly with $dev-flow-codex:dev-flow; the selector never skips assessment. Explicit Task resume and receipt-backed…