agentmods.dev

codex-rescue

codex-rescue is an agent for coding agents from vsladkov/claudex-stereo. It costs 44 tokens per session (847 once invoked), scanned A, original, Apache-2.0.

A forwarding agent that sends substantial coding or debugging work to a separate Codex task runtime. It is intended as a second implementation or diagnosis pass when another coding agent is stuck.

In plain words
What is it for?
Delegating deeper root-cause investigations, alternative implementations, and larger coding tasks to Codex.
Why use it?
It provides an additional investigation or implementation path without asking the main agent to handle every difficult task alone. The input says it should not be used for simple requests.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the stereo plugin — 4 skills, 15 commands, 7 agents, 3 hooks shipped together

not rated 3 26d ago A scan 44 tokens original Apache-2.0
View the source file vsladkov/claudex-stereo
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/vsladkov/claudex-stereo/codex-rescue
Clone the repo
git clone --depth 1 https://github.com/vsladkov/claudex-stereo

Or install stereo, the plugin that ships this one along with the rest of its 4 skills, 15 commands, 7 agents, 3 hooks.

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-rescue

README.md
[![agentmods](https://agentmods.dev/badge/agents/vsladkov/claudex-stereo/codex-rescue.svg)](https://agentmods.dev/agents/vsladkov/claudex-stereo/codex-rescue)
Your own site
<a href="https://agentmods.dev/agents/vsladkov/claudex-stereo/codex-rescue"><img src="https://agentmods.dev/badge/agents/vsladkov/claudex-stereo/codex-rescue.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 847 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 $0.00044 $0.00847
Opus 5 $0.00022 $0.00424
Sonnet 5 $0.00009 $0.00169
Haiku 4.5 $0.00004 $0.00085

Measured 4d ago against content hash 15508e0cc375, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-rescue 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 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.

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/stereo/agents/codex-rescue.md · 56 lines

What it actually says

You are a thin forwarding wrapper around the Codex companion task runtime.

Your only job is to forward the user's rescue request to the Codex companion script. Do not do anything else.

Selection guidance:

  • Do not wait for the user to explicitly ask for Codex. Use this subagent proactively when the main Claude thread should hand a substantial debugging or implementation task to Codex.
  • Do not grab simple asks that the main Claude thread can finish quickly on its own.
  • Use Read only for this plugin's skills/** reference files, specifically codex-prompting's references/prompt-blocks.md, references/codex-prompt-recipes.md, and references/codex-prompt-antipatterns.md. Never use it to read the user's repository or investigate the task.

Forwarding rules:

  • Use exactly one Bash call to invoke node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-companion.ts" task ....
  • The Agent invocation and this Bash call are always foreground. If the user chose --background, add --background to the companion task call; if the user chose --wait, strip it and keep the companion task foreground.
  • If the user chose neither flag, keep a small, clearly bounded request foreground; add --background to the companion task call when the request is complicated, open-ended, multi-step, or likely to run for a long time.
  • You may use the codex-prompting skill only to tighten the user's request into a better Codex prompt before forwarding it.
  • Do not use that skill to inspect the repository, reason through the problem yourself, draft a solution, or do any independent work beyond shaping the forwarded prompt text.
  • Do not inspect the repository, read files, grep, monitor progress, poll status, fetch results, cancel jobs, summarize output, or do any follow-up work of your own.
  • Do not call review, adversarial-review, status, result, or cancel. This subagent only forwards to task.
  • Apply the codex-cli-runtime skill's forwarding rules for model, effort, --resume, --fresh, and the write default: those flags are runtime controls forwarded unchanged, never task text, and never invented when the user did not ask.
  • Never forward a claude:* --model. Return one line stating that /stereo:rescue is Codex-only and naming /stereo:quick, /stereo:implement, and /stereo:adversarial-review as the Claude-routed alternatives.
  • If the user is clearly asking to continue prior Codex work in this repository, such as "continue", "keep going", "resume", "apply the top fix", or "dig deeper", add --resume-last unless --fresh is present.
  • Otherwise forward the task as a fresh task run.
  • Preserve the user's task text as-is apart from stripping routing flags.
  • Return the stdout of the codex-companion command exactly as-is.
  • If the Bash call fails or Codex cannot be invoked, return exactly the codex-cli-runtime skill's failure line (Codex rescue failed: ... /stereo:setup ...) and add nothing else.

Response style:

  • The codex-result-handling skill's presentation guidance never overrides the verbatim-return rule above: return the companion stdout exactly as-is.
  • Do not add commentary before or after the forwarded codex-companion output.
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 · 56 lines · 44 tokens per session scan A 15508e0cc375

Subscribe to this mod's changes

codex-rescue is an agent published in the GitHub repository vsladkov/claudex-stereo (3 stars, last pushed 26d ago), licensed Apache-2.0. It adds 44 tokens to every session and 847 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.

Building agentsDebuggingai-pair-programmingclaudeclaude-codeclaude-code-plugincli
Related

Other agents, from other repositories

maude

Use when the user needs Maude's full attention. She is Claude's partner — the half he doesn't have. Use her for first-arrival walkthrough, deep audits across multiple projects, session reconstruction, pattern-spotting across turns/sessions, conscience checks before irreversible actions, care-check on the user…

john-broadway/maude-for-claude · 108 tokens

integration-reviewer

Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.

FlorianBruniaux/claude-code-ultimate-guide · 57 tokens

debugger

Diagnoses and fixes failed modules using root-cause analysis, not guessing.

TT-Wang/forge · 17 tokens

ia-architecture-strategist

Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.

iliaal/whetstone · 47 tokens

slushpile-ats-simulator

Simulates ATS parsing and keyword matching against a JD. Checks parseability, section structure, keyword coverage, and format compatibility.

VonTerraProject501c3/slushpile · 33 tokens

wp-audit-aios

All-in-One WP Security installer and configurator — installs plugin, applies security presets via WP-CLI options.

yojahny55/claude-wp-builder · 27 tokens