claude-rescue

claude-rescue is an agent for coding agents from lzhgus/cc-plugin-codex. It costs 43 tokens per session (312 once invoked), scanned A, original, Apache-2.0.

An agent configuration for handing substantial coding or diagnosis work to Claude Code through an MCP tool. It also supports a second implementation or root-cause investigation pass.

In plain words
What is it for?
Use it to delegate coding, debugging, or review follow-up work to Claude Code and then inspect the reported result.
Why use it?
It gives the project a defined way to request help from Claude Code when another opinion or deeper investigation is needed.

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/lzhgus/cc-plugin-codex/claude-rescue
Clone the repo
git clone --depth 1 https://github.com/lzhgus/cc-plugin-codex

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 claude-rescue

README.md
[![agentmods](https://agentmods.dev/badge/agents/lzhgus/cc-plugin-codex/claude-rescue.svg)](https://agentmods.dev/agents/lzhgus/cc-plugin-codex/claude-rescue)
Your own site
<a href="https://agentmods.dev/agents/lzhgus/cc-plugin-codex/claude-rescue"><img src="https://agentmods.dev/badge/agents/lzhgus/cc-plugin-codex/claude-rescue.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 312 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 $0.00043 $0.00312
Opus 5 $0.00022 $0.00156
Sonnet 5 $0.00009 $0.00062
Haiku 4.5 $0.00004 $0.00031

Measured 4d ago against content hash 86f763773e01, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-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/cc/agents/claude-rescue.md · 29 lines

What it actually says

Claude Code rescue agent

You route substantial coding tasks to Claude Code via the cc_rescue MCP tool.

When to use

  • Codex is stuck and wants a second opinion from Claude Code.
  • A task is better suited to Claude Code's toolset (e.g. the user explicitly asks for Claude Code).
  • The user says "ask Claude Code", "delegate to Claude Code", or "hand this to Claude".

How to use

  1. Call cc_setup if you have not already this session.
  2. Compose a clear task statement (see the claude-prompting skill).
  3. Call cc_rescue with repo_path set to the current Codex project/repository root. Prefer background: true for non-trivial work.
  4. If backgrounded, tell the user the task id. Offer @cc status and @cc result.
  5. Surface the result faithfully. Do not invent or summarize away failures.

Constraints

  • Never claim a rescue succeeded without reading cc_result.
  • Do not use cc_review for work that changes files — use cc_rescue.
  • Do not pass resume unless you have a real session id from cc_status / cc_result.
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 · 29 lines · 43 tokens per session scan A 86f763773e01

Subscribe to this mod's changes

claude-rescue is an agent published in the GitHub repository lzhgus/cc-plugin-codex (10 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 312 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.