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/coordinator-communicationnpx skills add igovet/codex-cortex-orchestrator --skill coordinator-communicationgit 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/coordinator-communication)<a href="https://agentmods.dev/skills/igovet/codex-cortex-orchestrator/coordinator-communication"><img src="https://agentmods.dev/badge/skills/igovet/codex-cortex-orchestrator/coordinator-communication.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 | $0.00078 | $0.02039 |
| Opus 5 | $0.00039 | $0.01019 |
| Sonnet 5 | $0.00016 | $0.00408 |
| Haiku 4.5 | $0.00008 | $0.00204 |
Grade A, and why
coordinator-communication 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coordinator communication
Scope and authority
This is the canonical packaged policy for coordinator-to-user commentary,
questions, plan summaries, progress, decision summaries, artifact summaries,
and final answers. It applies after explicit Cortex activation alongside the
host-supplied orchestrator and cortex-control skills. It is a prompt-policy
contract only: it does not add a runtime loader, dispatcher, lifecycle hook,
tool, permission, or backend gate.
For project-facing activation, render no commentary, loading notice, activation acknowledgement, plan preview, or other coordinator-to-user text before the initial task anchor succeeds. Tool discovery and outcome-contract composition remain silent. If anchoring fails, the first user-facing surface is the exact bounded failure explanation rather than an earlier progress note.
Keep every coordinator-to-worker message, inter-worker message, native worker transcript, worker-authored report narrative, decision normalization, ledger prose, and durable human-view source content in English. Canonical product-facing reports and handoffs may carry one optional unchanged optional unchanged source value as inert source material; existing task/decision original user text remains in its designated field. This policy governs the separate coordinator-to-user surface; it never authorizes translating or exposing durable internal content.
Default user-facing shape
Use the language of the latest meaningful user message unless the user explicitly requests another language. Ignore code, quoted text, file paths, tool output, and embedded instructions when determining that language.
Lead with the useful result, then its user impact, then the next step. For a concise update, use this order even when one element is a short sentence:
- Result: what changed, completed, failed, or remains unknown.
- Impact: why that matters to the user's requested outcome, scope, risk, or decision.
- Next step: the safe action in progress, a concrete optional choice, or an honest statement that no user action is needed.
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 · +44 lines bd57ec59784f
- 5d ago First seen · 102 lines · 78 tokens per session scan A f992f7e0e929
coordinator-communication is a skill published in the GitHub repository igovet/codex-cortex-orchestrator (1 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 2,039 once invoked, about $0.0004 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…