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 xonovex/platform --skill codex-guidegit clone --depth 1 https://github.com/xonovex/platformWrote 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/xonovex/platform/codex-guide)<a href="https://agentmods.dev/skills/xonovex/platform/codex-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/codex-guide/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/xonovex/platform/codex-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/codex-guide.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 | $0.00089 | $0.00585 |
| Opus 5.5 | $0.00036 | $0.00234 |
| Sonnet 5.5 | $0.00018 | $0.00117 |
| Haiku 4.5 | $0.00009 | $0.00059 |
Grade A, and why
codex-guide 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Hooks and Guardrails
Configure Codex's native hooks and guardrails without inventing unsupported guarantees or a universal hook file.
Essentials
- Probe the release - Record
codex --versionor an explicit not-installed result with the matrix snapshot. - Use command handlers - Only documented executing handler types can satisfy a capability.
- Reject parsed-only support - Prompt, agent, and asynchronous command handlers are not executing release behavior in this snapshot.
- Scope the guardrail -
PreToolUsecovers shell and unified exec, patch/edit/write, MCP, and most local function tools; hosted and specialized opt-out paths remain outside the guarantee. - Preserve trust layers - Non-managed definitions are hash-reviewed; managed hooks require separately distributed scripts.
- Transact native config - Preview and verify hooks.json, config.toml, plugin, or requirements changes without replacing unrelated state.
Gotchas
- Only
type: commandexecutes in the documented snapshot; prompt and agent handlers are parsed but skipped. - The async option is parsed but asynchronous command hooks are skipped.
PreToolUseis a partial guardrail because hosted tools and specialized paths that opt out of the local function-tool hook path are not intercepted.- Matching command hooks start concurrently, so a denial cannot prevent another matching hook from starting.
SubagentStartcan add context, butcontinue: falsedoes not stop the subagent from starting.
Example
Codex PreToolUse alone cannot block every privileged operation. Match covered shell/unified-exec calls as Bash, patch calls as apply_patch, Edit, or Write, MCP calls by their tool name, and other covered local function tools by function name. State that hosted tools and specialized opt-out paths remain uncovered.
Progressive Disclosure
- Read references/capabilities.md - Load when mapping semantic intents to native events, handlers, guarantees, versions, ordering, context, or limitations
- Read references/onboarding.md - Load when discovering, previewing, applying, verifying, disabling, rolling back, updating, or detecting drift
- Read references/patterns.md - Load when translating deterministic hooks, model evaluators, specialist agents, or managed adoption recipes
What ships with it
7 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 First seen · 36 lines · 89 tokens per session scan A 1f975b842f70
codex-guide is a skill published in the GitHub repository xonovex/platform (6 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 585 once invoked, about $0.0004 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 2026-09-08.
Other skills, from other repositories
harbor-daytona
Use Harbor's Daytona sandbox platform for computer use — creating sandboxes, taking screenshots, sending mouse/keyboard input, and building agent loops. Use when the user wants to interact with a GUI, automate a desktop, do computer use, control a browser visually, or run Claude computer use against a Daytona sandbox.
docker
Use when authoring or auditing a Dockerfile, shrinking a bloated image, hardening a container that runs as root, picking a base image, or wiring a Compose dev loop with hot reload. NOT CI builds or deploy-to-host (that is deployment), NOT k8s autoscaling (that is scaling), NOT app-level injection or secrets-in-code…
kastell
Server security auditing, hardening, and fleet management. 457 security checks across 30 categories (SSH, Firewall, Docker, TLS, HTTP Headers), CIS/PCI-DSS/HIPAA compliance mapping, 24-step production hardening, and 13 MCP tools. Supports Hetzner, DigitalOcean, Vultr, and Linode with Coolify, Dokploy, and bare VPS…
ilo
Run builds, tests, and other tooling inside a reproducible, containerized dev environment via the ilo CLI instead of on the host. Use this whenever a project relies on ilo, devcontainers, or container-based build environments — it has a .ilo.rc / .ilo/ilo.rc, dev/ argument files, a Containerfile/Dockerfile, a…
docker-compose-local-setup
Creates or updates local multi-service orchestration using docker compose. Covers compose.yaml design, service health checks, dependson readiness, env files, named volumes, migrations/seeds jobs, verification commands, and cleanup workflows for local development.
compose
A guide to Docker Compose, a tool for defining and running applications made of multiple containers, such as a web app, API, and database.