codex-invocation

codex-invocation is a skill for Claude Code, Codex from strigov/superpowers-strigov-ver. It costs 77 tokens per session (4,047 once invoked), scanned B, original, MIT.

A guide for invoking the Codex command-line tool through a local wrapper. It explains how to start background coding or review jobs and monitor their progress.

In plain words
What is it for?
Use it whenever a workflow needs to dispatch a Codex task, review, or adversarial review from the command line.
Why use it?
It avoids unreliable direct invocation paths and keeps job state in the expected location. It also specifies model and polling settings for the supported workflow.

Skill for Claude CodeCodex

Part of the superpowers-strigov-ver plugin — 16 skills, 1 command shipped together

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/strigov/superpowers-strigov-ver/codex-invocation
Any agent
npx skills add strigov/superpowers-strigov-ver --skill codex-invocation
Clone the repo
git clone --depth 1 https://github.com/strigov/superpowers-strigov-ver

Made for: Claude Code, Codex.

Or install superpowers-strigov-ver, the plugin that ships this one along with the rest of its 16 skills, 1 command.

Wrote 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.

agentmods badge for codex-invocation

README.md
[![agentmods](https://agentmods.dev/badge/skills/strigov/superpowers-strigov-ver/codex-invocation.svg)](https://agentmods.dev/skills/strigov/superpowers-strigov-ver/codex-invocation)
Your own site
<a href="https://agentmods.dev/skills/strigov/superpowers-strigov-ver/codex-invocation"><img src="https://agentmods.dev/badge/skills/strigov/superpowers-strigov-ver/codex-invocation.svg" alt="Measured on agentmods" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,047 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00077 $0.04047
Opus 5 $0.00039 $0.02024
Sonnet 5 $0.00015 $0.00809
Haiku 4.5 $0.00008 $0.00405

Measured 4d ago against content hash 3de0cf166b11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex-invocation scanned grade B with 1 finding 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

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

cat ~/.claude/plugins/data/superpowers-strigov-ver-codex/state/<workspace-slug>/jobs/task-XXXX.log
skills/codex-invocation/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex invocation (codex-dispatch wrapper, background-only)

The plugin vendors the Codex companion runtime under vendor/codex-companion/ and exposes it through the codex-dispatch shell wrapper in bin/. Do not call the upstream OpenAI codex plugin — we do not depend on it being installed.

The wrapper handles three things on every call:

  1. Resolves the bundled codex-companion.mjs from the marketplace cache or the local dev tree.
  2. Pins CLAUDE_PLUGIN_DATA to ~/.claude/plugins/data/superpowers-strigov-ver-codex so jobs/broker state stays isolated from any other codex install on the machine.
  3. For task/review/adversarial-review, injects --model gpt-5.6-sol (overridable via CODEX_DEFAULT_MODEL env or by passing an explicit --model flag). This blocks the backend from auto-downgrading to spark on small or low-effort tasks. Protocol dispatches always pass an explicit --model per role (see the role table below); the pin only backs up ad-hoc calls like codex-ask.

On this Mac in Claude Code terminal mode, the standard Codex invocation paths silently auto-reject. Use this wrapper with background tasks and Monitor polling.

Working path

1. Resolve the wrapper once per session

DISPATCH="$(command -v codex-dispatch || true)"
[ -z "$DISPATCH" ] && DISPATCH="$(ls -1d ~/.claude/plugins/cache/strigov-cc-plugins/superpowers-strigov-ver/*/bin/codex-dispatch 2>/dev/null | sort -rV | head -1)"
[ -z "$DISPATCH" ] && DISPATCH="$(pwd)/bin/codex-dispatch"
echo "DISPATCH=$DISPATCH"

command -v codex-dispatch works when the marketplace install put bin/ in PATH; the glob fallback covers a fresh session before PATH refreshes; the $(pwd)/bin/... fallback is for local dev runs from the repo root.

2. One-time login (user action)

User runs in their shell prompt:

!codex login

The !-prefix in Claude Code makes it a user-shell command, not a tool call. Browser OAuth flow, then "Successfully logged in". Required once per machine. This logs in the standalone codex CLI (npm i -g @openai/codex), which is the only external dependency of the wrapper.

Read the full file on GitHub · 226 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. 4d ago First seen · 226 lines · 77 tokens per session scan B 3de0cf166b11

Subscribe to this mod's changes

codex-invocation is a skill published in the GitHub repository strigov/superpowers-strigov-ver (4 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 4,047 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens