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.
npx agentmods add skills/patrickserrano/lacquer/claude-rescuenpx skills add patrickserrano/lacquer --skill claude-rescuegit clone --depth 1 https://github.com/patrickserrano/lacquerWrote 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.
[](https://agentmods.dev/skills/patrickserrano/lacquer/claude-rescue)<a href="https://agentmods.dev/skills/patrickserrano/lacquer/claude-rescue"><img src="https://agentmods.dev/badge/skills/patrickserrano/lacquer/claude-rescue.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.00649 |
| Opus 5 | $0.00028 | $0.00324 |
| Sonnet 5 | $0.00011 | $0.00130 |
| Haiku 4.5 | $0.00006 | $0.00065 |
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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Rescue
A thin forwarding wrapper around the Claude Code CLI, for use from Codex. Your only job is to forward the task and return Claude's output. Do not inspect the repo, read files, draft your own solution, or do any independent analysis — that defeats the purpose of getting a second, independent opinion.
When to use
- Proactively, when stuck: a recurring error, an approach that isn't converging, or a task that would benefit from a different reasoning system's take.
- Don't grab a task you (Codex) can finish quickly yourself — this is a rescue mechanism, not a first resort.
How to forward
scripts/claude-companion.sh task "<the task, verbatim>" [--background|--wait] [--model <model>] [--resume|--fresh] [--write|--read-only]
- Preserve the task text as-is; strip only the routing flags below before forwarding.
- Foreground vs background:
--wait(default) blocks and prints the result — use for a small, bounded ask.--backgroundstarts a detached Claude Code agent and returns an id immediately (claude agents/claude attach <id>/claude logs <id>/claude stop <id>) — use for anything open-ended, multi-file, or long-running. --model: leave unset by default. Only pass a value on explicit request (opus,sonnet,fable).--write/--read-only:--write(default) runs with--permission-mode acceptEdits. Use--read-only(--permission-mode plan) when the ask is explicitly diagnosis/review-only, no edits.--resume/--fresh:--fresh(default) starts a new Claude Code session. Use--resume(claude -c) only when continuing a prior rescue in the same repo — "keep going", "apply the top fix", "dig deeper".- Return the script's output exactly as printed. No added commentary before or after it. If the call fails, surface the raw failure — don't paper over it or retry silently.
Source: mirror of the codex-rescue agent in openai/codex-plugin-cc, direction reversed (Claude → Codex becomes Codex → Claude) and adapted to Codex's skill-based extensibility model.
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.
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.
- 5d ago First seen · 51 lines · 57 tokens per session scan A 8bd89e7ffeba
claude-rescue is a skill published in the GitHub repository patrickserrano/lacquer (3 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 649 once invoked, about $0.0003 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.
Other skills, from other repositories
build-and-test
Build, lint, and test manzanasd - the Go toolchain gate every PR must pass, the CI matrix (Linux + macOS), and how to build the simbridge helper. Use before opening any PR to this repo or when debugging CI failures.
install-mimi-remote
安装、配置、配对、迁移、升级、诊断、回滚或卸载 Mimi Remote；在 macOS 上安装和维护 Mimi Remote Mac 菜单栏 App / DMG，或通过 Homebrew、Linux user-systemd 部署 agentd；从源码构建 iPhone/iPad App；配置 Codex 主通道和可选 Claude Code 实验 Runtime。用户提出“安装 Mimi Remote”“安装或修复 Mac 菜单栏 App”“在 iPad/iPhone 上使用 Codex 或 Claude Code”“部署、迁移或修复 agentd”“升级、回滚、卸载 Mimi Remote”“构建 MimiRemote iOS…
install-mimi-remote
安装、配置、配对、迁移、升级、诊断、回滚或卸载 Mimi Remote；在 macOS 上安装和维护 Mimi Remote Mac 菜单栏 App / DMG，或通过 Homebrew、Linux user-systemd 部署 agentd；从源码构建 iPhone/iPad App；配置 Codex 主通道和可选 Claude Code 实验 Runtime。用户提出“安装 Mimi Remote”“安装或修复 Mac 菜单栏 App”“在 iPad/iPhone 上使用 Codex 或 Claude Code”“部署、迁移或修复 agentd”“升级、回滚、卸载 Mimi Remote”“构建 MimiRemote iOS…
ast-grep
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
pinchtab-stealth-score
Run the PinchTab stealth-score sweep against 15 bot-detection / fingerprint sites (sannysoft, rebrowser, deviceandbrowserinfo, iphey, whoer, browserscan, pixelscan, fingerprint-scan, incolumitas, fvision, amiunique, browserleaks, creepjs, coveryourtracks, fingerprint-demo). Starts a Docker PinchTab container per…