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/cortex-controlnpx skills add igovet/codex-cortex-orchestrator --skill cortex-controlgit clone --depth 1 https://github.com/igovet/codex-cortex-orchestratorWhat 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 | $0.00027 | $0.00572 |
| Opus 5 | $0.00014 | $0.00286 |
| Sonnet 5 | $0.00005 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
cortex-control 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cortex Control Activation Kernel
This companion is host-supplied only after explicit cortex:orchestrator
selection. Do not select it for ordinary work or fetch it through a tool. All
worker communication, reports, ledger prose, and durable tool-authored strings
are English; coordinator-facing communication follows the latest meaningful
user language.
The active MCP registry is authoritative for the semantic call contract.
Mode boundary
The coordinator kernel below applies only to coordinator mode after direct
user route selection. A server-issued assignment_worker native child is a
separate mode: it does not activate or reopen the coordinator route, and it
cannot anchor tasks, govern, ask users, delegate, dispatch, or close. Its
first semantic action is assignment-evidence consumption from the exact
server-rendered dispatch brief. Only after the server confirms that evidence
may it perform assigned work and publish its owned outcome.
Pre-anchor protocol
Task anchoring precedes every task-scoped semantic operation. This includes clarification holds and questions, plan or approval holds, steering, governance, knowledge routing, delegation, worker dispatch, and closure preparation. A clarification needed before planning is opened and presented after the task anchor and before planner dispatch; it is a hold on the anchored task, not an alternative to opening it. Before the anchor, allow only complete contract composition, the single task-opening attempt, and read-only reconciliation of that same attempt after explicitly ambiguous transport.
For project-facing work, the first project execution action is exactly one task-opening operation from the live advertised schema. Compose the complete outcome contract, make that opening call, and require its successful command receipt and task anchor before knowledge routing, project reads, adaptation, governance, delegation, worker dispatch, or any other project execution.
Prose activation acknowledgement is not evidence. Shell or repository inspection before the anchor is a route violation. If transport is ambiguous, reconcile the same opening attempt read-only; never create a second task. If no anchor can be established, stop rather than starting degraded work.
What ships with it
2 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.
- 2d ago First seen · 57 lines · 27 tokens per session scan A 7a4e397849b1
cortex-control is a skill published in the GitHub repository igovet/codex-cortex-orchestrator (1 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 572 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 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.
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.
goal-flight
Portable Goal Flight workflow for long-running repo work: planning, dispatch, review, recovery, file-backed resume.
agent-orchestrator-v2
Agent Orchestrator workflow skill. Use this skill when the user needs Meta-skill que orquestra todos os agentes do ecossistema. Scan automatico de skills, match por capacidades, coordenacao de workflows multi-skill e registry management and the operator should preserve the upstream workflow, copied support files, and…