skill-patrickserrano-lacquer-claude-rescue · by Install
$ agentstack add skill-patrickserrano-lacquer-claude-rescue ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-patrickserrano-lacquer-claude-rescue) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
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 "" [--background|--wait] [--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. --background starts a detached Claude Code agent and returns an id immediately (claude agents / claude attach / claude logs / claude stop ) — 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.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: patrickserrano
- Source: patrickserrano/lacquer
- License: MIT
- Homepage: https://patrickserrano.github.io/lacquer/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.