message-codex

A guide for sending a short message from Claude Code, another agent, or a script to an existing Codex session. It explains how to find the exact session and queue the message.

In plain words
What is it for?
Use it when another tool or agent needs to report information to a particular Codex session.
Why use it?
It avoids sending a message to the wrong session or confusing message delivery with restarting or resuming a session.

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

Made for: Claude Code, Codex.

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 641 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00101 $0.00641
Opus 5 $0.00051 $0.00320
Sonnet 5 $0.00020 $0.00128
Haiku 4.5 $0.00010 $0.00064

Measured yesterday against content hash 0f4e2b2d15bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

message-codex 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 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.

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.

plugins/heapy/skills/message-codex/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Message Codex

Find the exact Codex session and queue it one plain-text message through Codex app-server.

For the opposite direction, use Message Claude.

If the target belongs to the current Codex agent tree and an inter-agent messaging tool is available, use that tool. Do not use the CLI to bypass a permission rule that denied it. The workflow below is for separate Codex sessions and external callers such as Claude Code or a script.

Send a message

  1. Check that this Codex CLI supports session messaging:

    codex queue --help
    

    If queue is unavailable, report that the installed CLI does not support this workflow. Do not substitute codex exec resume: resuming a session is not the same as queueing a message to it.

  2. Browse sessions on the shared local app-server daemon:

    codex agents --no-alt-screen
    

    Open the candidate and run /status to copy its Session UUID, then exit that TUI. A preview helps recognize a session but is not an identifier.

  3. Select the target by its exact session name or UUID. Prefer the UUID when names repeat, and never guess between multiple matches.

  4. Queue one short message:

    codex queue \
      --thread the-session-name-or-uuid \
      --message 'claude: the migration finished; tenant_id is the new column'
    

For a different app-server, pass the same --remote endpoint to both agents and queue. When that server requires authentication, also pass --remote-auth-token-env with the name of the environment variable containing its bearer token; never put the token itself on the command line.

Failures

  • No matching session: check that the target uses the same app-server, or verify the remote endpoint. Do not choose a merely similar name.
  • Daemon connection failure: report it instead of starting, resuming, or forking another session.
  • Permission error: request access scoped to the app-server endpoint; do not bypass the sandbox.
  • Successful command: report the message as queued, not processed. The target may not act on it immediately.

Read the full file on GitHub · 64 lines

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 · 64 lines · 101 tokens per session scan A 0f4e2b2d15bd

Subscribe to this mod's changes

message-codex is a skill published in the GitHub repository Heapy/kortex (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 101 tokens to every session and 641 once invoked, about $0.0005 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.

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

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

compose-side-effects

Use when writing or reviewing Jetpack Compose code with LaunchedEffect, DisposableEffect, SideEffect, rememberCoroutineScope, rememberUpdatedState, snapshotFlow, snackbar, navigation, focus requests, analytics, or event Flow collection. Technique-layer skill — complements the codebase-specific compose-expert.

vitorpamplona/amethyst · 62 tokens