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.
git clone --depth 1 https://github.com/wildcard/caroWrote 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/agents/wildcard/caro/caro-frustrated-beta)<a href="https://agentmods.dev/agents/wildcard/caro/caro-frustrated-beta"><img src="https://agentmods.dev/badge/agents/wildcard/caro/caro-frustrated-beta/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.
<a href="https://agentmods.dev/agents/wildcard/caro/caro-frustrated-beta"><img src="https://agentmods.dev/badge/agents/wildcard/caro/caro-frustrated-beta.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.03120 |
| Opus 5 | $0.00000 | $0.01560 |
| Sonnet 5 | $0.00000 | $0.00624 |
| Haiku 4.5 | $0.00000 | $0.00312 |
Grade C, and why
caro-frustrated-beta scanned grade C with 1 finding 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 8d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **You do not retry destructive commands.** If `caro` generates `rm -rf`, The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 8d ago First seen · 234 lines · 0 tokens per session scan C ce17c0e90c74
caro-frustrated-beta is an agent published in the GitHub repository wildcard/caro (37 stars, last pushed today), licensed AGPL-3.0. It costs nothing until one of its globs matches a file; then it loads 3,120 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other agents, from other repositories
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.
policy-tester
Simulate a Spacelift policy against synthesized inputs and report the decision.
bug-verifier-agent
Expert in verifying bug fixes. Use when a bug has been fixed and needs confirmation that the solution works and introduces no regressions.
dangerous-agent
An agent with security issues for testing.
visual-reviewer
Visual regression reviewer that compares live web pages against Figma designs. Takes screenshots of both, runs pixel-level diff, and uses AI vision to evaluate whether differences are bugs or acceptable variations. Use before merge or deployment to catch visual regressions.
qa
Quality assurance specialist. Use this agent for test planning, test execution, Playwright test suite creation with video recording, API testing, validating implementations against product feature files, and comprehensive flow testing. Has browser access for manual testing. Context: Code is ready for validation user…