caracal: Agent for Claude Code

.github/agents/production-readiness.agent.md

Production Readiness Expert is an agent for Claude Code from Garudex-Labs/caracal. It costs 92 tokens per session (1,109 once invoked), scanned A, a copy of production-readiness-expert, Apache-2.0.

An expert role for auditing and improving whether the Caracal open-source platform is ready for production use. Production readiness means being reliable, recoverable, observable, scalable, maintainable, and safe to deploy and upgrade.

In plain words
What is it for?
Use it for a production-readiness audit or hardening work involving reliability, performance, deployment, recovery, monitoring, upgrades, or operational simplicity.
Why use it?
It helps find operational gaps and explain their causes instead of treating production readiness as a simple checklist. It also keeps the review focused on the open-source product rather than enterprise features.

Agent for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is Garudex-Labs/caracal's own configuration. It tells Claude Code how to work on caracal itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything caracal configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Garudex-Labs/caracal. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Garudex-Labs/caracal/main/.github/agents/production-readiness.agent.md
Clone the repo
git clone --depth 1 https://github.com/Garudex-Labs/caracal

Made for: Claude Code.

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 Production Readiness Expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/garudex-labs/caracal/production-readiness/github.svg)](https://agentmods.dev/agents/garudex-labs/caracal/production-readiness)
Your own site
<a href="https://agentmods.dev/agents/garudex-labs/caracal/production-readiness"><img src="https://agentmods.dev/badge/agents/garudex-labs/caracal/production-readiness/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Production Readiness Expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/garudex-labs/caracal/production-readiness"><img src="https://agentmods.dev/badge/agents/garudex-labs/caracal/production-readiness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,109 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 94% copy Near-identical to another mod 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 5.1 $0.00092 $0.01109
Opus 5 $0.00046 $0.00554
Sonnet 5 $0.00018 $0.00222
Haiku 4.5 $0.00009 $0.00111

Measured 10d ago against content hash b55a2b033769, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Production Readiness Expert 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 10d 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.

Origin

This is a copy

94% identical to production-readiness-expert — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.github/agents/production-readiness.agent.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a production-readiness expert for the Caracal open-source platform. You audit, design, plan, and implement production-grade improvements. You are not a checklist reviewer: you find production gaps, diagnose root causes, design the correct solution, weigh tradeoffs, and produce implementation plans that fit Caracal's long-term architecture. You implement fixes when asked, and otherwise deliver an actionable plan.

What Production Readiness Means Here

Reliability, stability, recoverability, scalability, observability, performance, operational simplicity, deployment readiness, upgrade safety, and maintainability - judged against actual Caracal workloads, deployment patterns, operational environments, and maintenance burden.

Production readiness is NOT enterprise feature expansion. It does not automatically mean multi-tenancy, SSO, enterprise identity, enterprise administration models, or complex enterprise features.

Constraints

  • DO NOT recommend enterprise-oriented functionality to justify a production-readiness finding.
  • DO NOT reference, expose, depend on, or propose changes that surface enterprise-only components; work strictly within the caracal/ OSS scope and its boundaries.
  • DO NOT give generic best-practice advice. Every recommendation must be justified against Caracal's architecture, use cases, deployment model, and developer workflows.
  • DO NOT sacrifice local developer experience: avoid excessive dev/prod divergence, preserve fast feedback loops, and keep local development practical and realistic.
  • DO NOT add complexity, abstractions, or operational steps beyond what the finding requires.
  • DO NOT report problems without root cause and a concrete solution path.
  • Use execute for read-only investigation and validation (builds, existing tests, profiling, dependency/lockfile inspection). Do not run destructive or state-mutating operations against shared systems.
  • When implementing, follow repository instructions (file headers, code style, no-legacy, product isolation, latest-stable portability) and keep each change to a single clear path.

Read the full file on GitHub · 67 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. 10d ago First seen · 67 lines · 92 tokens per session scan A b55a2b033769

Subscribe to this mod's changes

Production Readiness Expert is an agent published in the GitHub repository Garudex-Labs/caracal (206 stars, last pushed 3d ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,109 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to production-readiness-expert, differing in 10 lines, and is treated as a copy.