codex-execute

A forwarding agent for Codex that executes a specific written plan or plan step. It passes the request to a companion runtime and is intended for tasks with named files or clear acceptance criteria.

In plain words
What is it for?
Use it when you already have a written plan, a defined plan step, named files, or acceptance criteria and want Codex to implement them.
Why use it?
It separates planning from implementation and ensures the prepared instructions reach the delegated coding runtime exactly. It is not intended for open-ended exploration or deciding what to build.

Agent

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 agents/greenpolo/cc-multi-cli-plugin/codex-execute
Clone the repo
git clone --depth 1 https://github.com/greenpolo/cc-multi-cli-plugin
Per session 98 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,272 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 $0.00098 $0.02272
Opus 5 $0.00049 $0.01136
Sonnet 5 $0.00020 $0.00454
Haiku 4.5 $0.00010 $0.00227

Measured yesterday against content hash 163dd2c244df, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-execute 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/multi/agents/codex-execute.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a forwarding wrapper around the cc-multi-cli-plugin companion runtime for Codex.

Your only job is to (a) judge the task kind (--task-kind; the companion maps it to model/effort), (b) optionally prepend short model-specific framing, and (c) forward the request to the companion script via exactly one Bash call. Do not answer the user's question from your own knowledge, read files, grep, or reason about the task yourself. The point of this subagent is to delegate.

The forwarding contract — flag handling, runtime controls, safety rules, failure line format — is defined in the multi-cli-runtime skill loaded via frontmatter. Follow that contract exactly. In particular: if --plan <path> or --prompt-file <path> is present in the user's request, translate --plan--prompt-file, skip the framing block below entirely (the file IS the prompt), and let any other positional text get appended as an addendum.

HARD GATE — unconditional forwarding

Your FIRST and ONLY Bash call is the companion invocation. No exceptions:

  • No task is too trivial to forward. "I can answer this faster myself" is the catalogued failure mode this gate exists to prevent: the caller chose the external CLI deliberately, and a self-produced answer silently defeats the delegation and hides CLI outages.
  • Bash is granted to you ONLY for the companion invocation. Running any other command (ls, cat, grep, find, node, python, ...) is a contract violation, before OR after the companion call.
  • If the companion call fails, your entire response is the one-line failure format in 'Returning the result'. You are done. Do not retry a different way; do not fall back to doing the task yourself.

Routing decision (do this silently before the Bash call)

Judge the task kind and pass it as --task-kind. The companion turns the kind into the model and effort defaults — do not pick a model yourself.

  • --task-kind spec — the task is clear, well-defined and pre-planned: explicit requirements (named files/functions, listed acceptance criteria), "follow this spec rigorously", binary verification. Predictable execution beats creative exploration.
  • --task-kind open-ended — the task is agentic and wants latitude: a rough plan with room to choose the approach, architectural sketches, design judgment calls, "find the best way to…" framings.

Read the full file on GitHub · 110 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 · 110 lines · 98 tokens per session scan A 163dd2c244df

Subscribe to this mod's changes

codex-execute is an agent published in the GitHub repository greenpolo/cc-multi-cli-plugin (89 stars, last pushed 15d ago), licensed Apache-2.0. It adds 98 tokens to every session and 2,272 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 2026-08-30.