call-codex

A guide for using the Codex command-line tool as either an independent code reviewer or a delegated task runner. A reviewer gives a separate opinion, while an executor makes a scoped repository change.

In plain words
What is it for?
Use it when asking another Codex process to challenge a finding, review code, or complete a defined task in the repository.
Why use it?
It helps choose the right mode and permissions, provide the necessary context, and verify the result without confusing review with implementation.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/heapy/kortex/call-codex
Any agent
npx skills add Heapy/kortex --skill call-codex
Clone the repo
git clone --depth 1 https://github.com/Heapy/kortex

Made for: Claude Code, Codex.

Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,874 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00122 $0.03874
Opus 5 $0.00061 $0.01937
Sonnet 5 $0.00024 $0.00775
Haiku 4.5 $0.00012 $0.00387

Measured yesterday against content hash 81f075a0478d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

call-codex scanned grade B with 2 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`~/.codex/config.toml` supplies defaults (`model`, `model_reasoning_effort`, `sandbox_mode`,

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `-c sandbox_workspace_write.network_access=true` — dependency resolution, `git fetch`, curl.
plugins/heapy/skills/call-codex/SKILL.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Call Codex

Two modes

Reviewer Executor
Job break a claim do a scoped task
Sandbox read-only, always workspace-write plus what the task needs
The output that matters the disagreement the diff
Verified by reading the code reading the diff and running the tests

One binary, one set of traps, two different grants and two different prompts. Picking the wrong grant is the usual failure: a reviewer with write access starts fixing instead of judging, and an executor without network dies on the first dependency fetch.

Prerequisites

Check which codex. Report and stop if it is absent.

~/.codex/config.toml supplies defaults (model, model_reasoning_effort, sandbox_mode, sandbox_workspace_write.*). Pass everything the run depends on explicitly anyway: behavior should not change because a default moved.


Mode 1 — Reviewer

A second reader for code that is already understood. Not a search tool, not a replacement for reading the code. It earns its cost in one situation: a claim exists — a review finding, a diagnosis, a design decision — and an independent model should try to break it.

Codex analyzes; the calling agent implements. Never let this mode write.

When to use

  • A review produced findings and their reliability matters before acting on them.
  • A diagnosis is plausible but unproven and a wrong fix would be expensive.
  • Two explanations of the same failure both fit and the difference changes the fix.
  • The user explicitly asks for codex.

When not to use

  • To find code or navigate a repository. Grep is faster and free.
  • To confirm something already verified. A run costs minutes and real tokens.
  • To decide anything the user has already decided.

Read the full file on GitHub · 284 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. yesterday First seen · 284 lines · 122 tokens per session scan B 81f075a0478d

Subscribe to this mod's changes

call-codex is a skill published in the GitHub repository Heapy/kortex (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 122 tokens to every session and 3,874 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

mobile-experience-report

Use when the user says 'my site looks bad on mobile', 'check mobile layout', 'responsive audit', or 'site broken on phones'. Diagnoses breakpoint problems, text sizing, column stacking failures, hidden elements, and navigation menu behavior, device by device.

respira-press/agent-skills-wordpress · 58 tokens

motherduck-design-dive

Design or redesign a MotherDuck Dive as a responsive, reusable analytics interface. Use when a Dive must be mobile-friendly from the start, support light and dark modes, reserve space for filters, use restrained Power BI-style information design, embed small charts inside metric components, or work across customers…

motherduckdb/agent-skills · 69 tokens

desktop-expert

Compose Multiplatform Desktop patterns for the desktopApp/ module. Use when working with (1) Desktop-only APIs (Window, WindowState, Tray, MenuBar, Dialog), (2) keyboard shortcuts and menu systems with OS-aware conventions (Cmd vs Ctrl, isMacOS branching), (3) desktop navigation (NavigationRail/sidebar vs Android…

vitorpamplona/amethyst · 157 tokens

gradle-expert

Build optimization, dependency resolution, and multi-module KMP troubleshooting for AmethystMultiplatform. Use when working with: (1) Gradle build files (build.gradle.kts, settings.gradle), (2) Version catalog (libs.versions.toml), (3) Build errors and dependency conflicts, (4) Module dependencies and source sets, (5)…

vitorpamplona/amethyst · 132 tokens

add-native

Public entry point for native device capabilities and native controls — camera, image picker, barcode/QR scanner, document picker, file picker, secure storage, file system, sharing, PDF generation/viewing, pen/signature capture, background GPS/geolocation tracking, or supported local file workflows — in a Power Apps…

microsoft/power-platform-skills · 96 tokens

amy-expert

Patterns for extending amy, the Amethyst CLI in cli/. Use when adding an amy command, touching files under cli/src/main/kotlin/…/cli/, wiring a new subcommand into Main.kt, writing an interop test script that drives Amy, or extracting logic out of amethyst/ into commons/ so a CLI command can call it. Enforces the…

vitorpamplona/amethyst · 217 tokens