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/chronoaiproject/nyxid/aevatar-codex-exec-node-setupnpx skills add ChronoAIProject/NyxID --skill aevatar-codex-exec-node-setupgit clone --depth 1 https://github.com/ChronoAIProject/NyxIDWhat 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 | $0.00088 | $0.03118 |
| Opus 5 | $0.00044 | $0.01559 |
| Sonnet 5 | $0.00018 | $0.00624 |
| Haiku 4.5 | $0.00009 | $0.00312 |
Grade A, and why
aevatar-codex-exec-node-setup 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 3d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure Aevatar codex_exec
Invocation gate
Continue only when the user explicitly asks to configure, repair, or prove a codex_exec target,
or explicitly invokes this skill. If this skill was selected speculatively, stop before mutation:
route feasibility questions to aevatar-feasibility-advisor and failure attribution to
aevatar-triage.
Choose exactly one target before changing state:
managed_sandbox: use for bounded one-shot work in an operator-selected, empty, ephemeral Git workspace. Explicitly prepare the eligible native NyxID user's invocation credential before normal execution; Aevatar then calls that user's exactchrono-sandboxUserService and receives a structured terminal result. No personal node or local Codex login is needed.private_ssh: use when work must access a user-owned fixed Git workspace, host files, or host Codex configuration. The user owns the private NyxID node, SSH service, principal, forced-command wrapper, and Codex authentication.
Never mix fields between targets. Do not report either target as ready until its public Ornn sample succeeds through Aevatar with exact CODEX_EXEC_READY.
Guardrails
- Never print, copy, or persist NyxID tokens, SSH private keys, Codex credentials, or
auth.jsoninto workflow input, logs, issue comments, or image layers. - Never let a workflow choose an image, provider, model flag, shell fragment, approval policy, workspace path, or sandbox bypass.
- Never ask a caller to supply a raw key or token. Use the authenticated managed-credential
lifecycle explicitly:
POST /api/managed-codex/credential, thenGET /api/managed-codex/credential. Normalcodex_execis credential-read-only and never provisions, reconciles, rotates, repairs, or retries credentials. - Keep a private node and SSH service personal unless the user explicitly authorizes organization ownership.
- For private SSH, use a dedicated SSH key, pinned host key, forced command, fixed Git workspace, and Codex
workspace-write; never add a dangerous sandbox bypass.
What ships with it
5 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.
- 3d ago First seen · 279 lines · 88 tokens per session scan A c2e02c6f26e5
aevatar-codex-exec-node-setup is a skill published in the GitHub repository ChronoAIProject/NyxID (36 stars, last pushed 4d ago), licensed Apache-2.0. It adds 88 tokens to every session and 3,118 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 2026-08-30.
Other skills, from other repositories
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
openspec-propose
Propose a new change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
xcodebuildmcp-structured-output-review
Use when reviewing XcodeBuildMCP structured output schema changes, schema versioning, manifest outputSchema metadata, and JSON fixture compatibility.