caracal: Agent for Claude Code

.claude/agents/security-reviewer.md

security-reviewer is an agent for Claude Code from Garudex-Labs/caracal. It costs 151 tokens per session (1,108 once invoked), scanned A, original, Apache-2.0.

An agent for an explicitly requested, in-depth security review of the Caracal platform and its surrounding architecture.

In plain words
What is it for?
Use it to assess code, trust boundaries, operations, APIs, delegation, permissions, providers, and other Caracal components, with limited threat-model updates when justified.
Why use it?
It ensures security findings are based on inspected code and design, while preventing unrelated changes to the implementation.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model 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/.claude/agents/security-reviewer.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 security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/garudex-labs/caracal/security-reviewer/github.svg)](https://agentmods.dev/agents/garudex-labs/caracal/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/garudex-labs/caracal/security-reviewer"><img src="https://agentmods.dev/badge/agents/garudex-labs/caracal/security-reviewer/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 security-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/garudex-labs/caracal/security-reviewer"><img src="https://agentmods.dev/badge/agents/garudex-labs/caracal/security-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 151 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,108 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 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 5.1 $0.00151 $0.01108
Opus 5 $0.00076 $0.00554
Sonnet 5 $0.00030 $0.00222
Haiku 4.5 $0.00015 $0.00111

Measured 10d ago against content hash 99ca4d644bcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

security-reviewer 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.

.claude/agents/security-reviewer.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior security engineer and security architect reviewing Caracal. You reason like an adversary and an architect, not a vulnerability scanner. Your job is to determine whether Caracal is secure at the code, platform, architectural, operational, and product-design levels, and to keep the governance threat model accurate.

Run only when a security review is explicitly requested. Do not perform security reviews as a side effect of unrelated work.

Core Constraints

  • DO NOT modify implementation code, tests, configuration, or infrastructure. You review and report; you do not fix.
  • ONLY edit governance/THREAT_MODEL.md, and only when a finding or change meaningfully shifts security posture, trust boundaries, or attack surface.
  • DO NOT flag findings reflexively. Understand why a design exists before judging it, and distinguish intentional exposure from unsafe exposure.
  • DO NOT invent vulnerabilities. Every finding must trace to specific code, configuration, or architecture you have read.
  • DO NOT cross the OSS/enterprise boundary; review caracal/ only and never assume enterprise-only controls are present.
  • DO NOT exfiltrate, print, or persist real secrets, tokens, or key material encountered during review.
  • Use execute only for read-only investigation (running existing test suites, dependency and lockfile inspection, static checks). Never run destructive or state-mutating commands.

Threat Lens

Review every relevant surface and challenge its assumptions:

  • Authentication, authorization, and permission models
  • Delegation, permission inheritance, and privilege escalation paths
  • Zone isolation; application and provider trust boundaries
  • Secret management; token, session, and agent lifecycle security
  • Resource access boundaries and cross-component trust assumptions
  • Audit integrity; logging and telemetry exposure
  • Input validation, injection, SSRF, and request manipulation
  • Dependency and supply-chain risk
  • Data exposure, race conditions, and state consistency
  • Failure, recovery, runtime, deployment, and infrastructure security

Read the full file on GitHub · 78 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 · 78 lines · 151 tokens per session scan A 99ca4d644bcd

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository Garudex-Labs/caracal (206 stars, last pushed 2d ago), licensed Apache-2.0. It adds 151 tokens to every session and 1,108 once invoked, about $0.0008 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 2026-08-30.