run-codex

A development skill that runs a real Codex session with a supplied prompt and captures its events and results.

In plain words
What is it for?
Use it to test event handlers, debug event processing, inspect response order and usage data, and validate implementation changes.
Why use it?
It helps developers check how Codex actually responds instead of relying only on mocked or assumed behavior.

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/agentprism/agentprism-workflows/run-codex
Any agent
npx skills add agentprism/agentprism-workflows --skill run-codex
Clone the repo
git clone --depth 1 https://github.com/agentprism/agentprism-workflows

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 631 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 $0.00039 $0.00631
Opus 5 $0.00019 $0.00316
Sonnet 5 $0.00008 $0.00126
Haiku 4.5 $0.00004 $0.00063

Measured 2d ago against content hash 96a1215812d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run-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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/run-codex-test.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

packages/codex-acp/.claude/skills/run-codex/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run Real Codex Test

This skill runs real Codex with a prompt and captures all events for analysis during development.

When to Use

  • Testing new event handlers
  • Debugging event processing issues
  • Understanding Codex response format and event order
  • Validating implementation changes against real Codex behavior
  • Seeing actual token usage, rate limits, and other metadata

How to Run

Execute the test script using npm:

npm run codex-test -- -p "Your prompt here"

Options

Option Short Description Default
--prompt -p Prompt to send to Codex (required) -
--cwd -c Working directory for the session Current dir
--output -o Output format: all, codex, acp, summary all
--json - Output events as JSON false
--help -h Show help message -

Examples

# See all events for a simple prompt
npm run codex-test -- -p "What files are in this directory?"

# Test with specific working directory
npm run codex-test -- -p "Read the README" -c /path/to/project

# See only Codex events (raw server notifications)
npm run codex-test -- -p "Hello" -o codex

# See only summary (token usage, timing, event counts)
npm run codex-test -- -p "Hello" -o summary

# Get JSON output for analysis with jq
npm run codex-test -- -p "Hello" --json | jq '.method'

Output

The script outputs events in real-time as they arrive:

  1. Codex Events ([CODEX]): Raw events from Codex app server

    • thread/started, turn/started, turn/completed
    • item/started, item/completed, item/agentMessage/delta
    • thread/tokenUsage/updated, account/rateLimits/updated
  2. ACP Events ([ACP]): Events sent to ACP connection

    • sessionUpdate with various update types
  3. Summary: Aggregated statistics

    • Stop reason, duration, event counts
    • Token usage breakdown (input, cached, output, reasoning, total)
    • Event type frequency

Read the full file on GitHub · 75 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. 2d ago First seen · 75 lines · 39 tokens per session scan A 96a1215812d8

Subscribe to this mod's changes

run-codex is a skill published in the GitHub repository agentprism/agentprism-workflows (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 39 tokens to every session and 631 once invoked, about $0.0002 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

add-acp-agent-support

Add first-class support for an ACP-compatible agent CLI to Intelligent Terminal. Use when integrating a new built-in AI agent, ACP server command, authentication flow, model selection, interactive delegation, session hooks, onboarding, Settings, branding, GPO policy, documentation, tests, build, deployment, or live…

microsoft/intelligent-terminal · 72 tokens

opentag

Use when installing, pairing, operating, or troubleshooting OpenTag through the published CLI, self-hosted Control Plane, governed completion, supported collaboration platforms, or built-in coding agents.

amplifthq/opentag · 40 tokens

claw-orchestrator

Manage persistent coding sessions across Claude Code, Codex, Antigravity (agy), Grok Build, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel…

Enderfga/claw-orchestrator · 468 tokens

ultraapp-interview

Use when the user opens a Forge tab in the claw-orchestrator dashboard to start building a new ultraapp. Drives a structured Q&A interview that produces a complete AppSpec, then signals readiness to build.

Enderfga/claw-orchestrator · 48 tokens

configure-coddy

Change Coddy's own configuration when the user asks for it: edit settings, providers, models, logging, permissions, or find, install, update, and remove MCP servers and skills. Stages UCI-style commands and commits only after the user confirms saving. Load when the user explicitly asks to change a Coddy setting, or…

coddy-project/coddy-agent · 106 tokens

adapt-acp-events

Normalize and adapt ACP Agent session/update events, especially toolcall and toolcallupdate differences, for FylloCode. Use when integrating a new ACP Agent, improving an existing Agent's tool activity display or user-facing tool titles, analyzing real ACP traces, adding or revising an Agent event adapter, or…

Fioooooooo/FylloCode · 95 tokens