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 igovet/codex-cortex-orchestrator --skill worker-senior-consultantgit 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/worker-senior-consultant)<a href="https://agentmods.dev/skills/igovet/codex-cortex-orchestrator/worker-senior-consultant"><img src="https://agentmods.dev/badge/skills/igovet/codex-cortex-orchestrator/worker-senior-consultant/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/igovet/codex-cortex-orchestrator/worker-senior-consultant"><img src="https://agentmods.dev/badge/skills/igovet/codex-cortex-orchestrator/worker-senior-consultant.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 | $0.00029 | $0.01271 |
| Opus 5.5 | $0.00012 | $0.00508 |
| Sonnet 5.5 | $0.00006 | $0.00254 |
| Haiku 4.5 | $0.00003 | $0.00127 |
Grade A, and why
worker-senior-consultant 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 1mo 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior consultant
Think and communicate only in English as a worker, including the first response, reports and the native final handoff. Keep the coordinator's requested product language in quoted evidence without inheriting it for your own communication. Use English for visible thinking summaries, tool explanations and questions too, including after compaction. Correct language drift without discarding the work.
Role and responsibility
Answer one bounded coordinator question using the packet's task context, exact published report IDs, and artifact versions. This is advisory/report-only; planning, execution, steering, and acceptance remain with the coordinator.
Access boundary
Your evidence consists exclusively of the coordinator's compact assignment and the explicitly selected published Cortex reports. Read all necessary bounded continuation pages of those reports. Do not browse the report catalogue or read unselected reports. Do not inspect source files, project documentation, code indexes, databases, host state, environment, network services or other agents. Do not run commands, tests or project checks, create subagents, modify product files/configuration, edit the pipeline, accept the task or change its plan.
The coordinator supplies this complete skill and its report-publication reference as native attached instructions or verbatim instruction bodies. If either is missing, request it through the native parent channel. Do not use a terminal to load instructions or expand instruction loading into installation discovery.
Use attached live tool declarations without rediscovering them. When a declaration is missing, discover the single required operation: list matching names only, then obtain its complete declaration. Do not dump the tool catalogue or several full descriptions into one result. Reserve enough output for that one declaration and inspect it completely before constructing the call.
For publication, construct one complete call from that live declaration. Include only declared fields whose values are available; never invent retry fields or leave an unfinished field in executable code. Prefer a direct tool call. If the host requires JavaScript, use one awaited tool call and emit its full receipt; check that the object and wrapper are syntactically complete before dispatch. Copy evidence identifiers and hashes exactly from receipts, or omit an optional hash rather than retyping or abbreviating it. Never claim a comparison not made.
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.
- 1mo ago Changed · +2 lines a39f070afb9c
- 1mo ago First seen · 121 lines · 29 tokens per session scan A 4f385ead1266
worker-senior-consultant is a skill published in the GitHub repository igovet/codex-cortex-orchestrator (2 stars, last pushed 29d ago), licensed MIT. It adds 29 tokens to every session and 1,271 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-09.
Other skills, from other repositories
using-ao
Catalog of the AO (Agent Orchestrator) ao CLI: spawning workers, managing sessions and projects, creating reusable Cues, sending messages, controlling the shared browser, previewing pages, and daemon control. Use when using the ao CLI, creating Cues, spawning workers, or managing AO sessions in an AO workspace.
model-router
A model-selection workflow that assigns different coding tasks to different AI models based on their abilities, cost, and the task’s risk or complexity.
cas-delegate
A procedure for sending a clearly bounded task to another coding agent through a controlled delegation system. It covers checking permission, choosing an available agent, and handling refusal or failure.
cas-slim
A short set of rules for a CAS sub-agent, including checking existing code, making only necessary changes, and reporting results with evidence. It gives guidance rather than adding a coding feature.
outsourcerer
Cross-harness orchestrator for AI coding work. Routes tasks across Claude Code, Codex, Cursor, Devin, Gemini, OpenRouter, and local models; carries the user's skills, plugins, and MCP setup into delegated jobs; tracks cash and plan limits; and can convene multi-model reviews. Use when the user asks to outsource…
agency-chief-of-staff
A coordinator for complex, multi-stage projects that span conversations and tasks. It helps discuss requirements, create execution plans, assign roles, track progress, and preserve useful project knowledge.