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 instructions/wildcard/caro/safetygit 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/instructions/wildcard/caro/safety)<a href="https://agentmods.dev/instructions/wildcard/caro/safety"><img src="https://agentmods.dev/badge/instructions/wildcard/caro/safety.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 | $0.01135 | $0.01135 |
| Opus 5 | $0.00567 | $0.00567 |
| Sonnet 5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade C, and why
caro safety.instructions.md scanned grade C with 4 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 2d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- `sudo su`, `sudo -i` - Shell escalation Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- `curl | bash`, `wget | sh` - Remote code execution Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `rm -rf /` - Recursive root deletion Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl | bash`, `wget | sh` - Remote code execution 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.
- 2d ago First seen · 160 lines · 1,135 tokens per session scan C 993ac9cad664
caro safety.instructions.md is an instructions file published in the GitHub repository wildcard/caro (37 stars, last pushed 2d ago), licensed AGPL-3.0. It adds 1,135 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it C with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
tokf CLAUDE.md
Claude Code instructions for mpecan/tokf, covering tokf — development guidelines, project philosophy, commits, code quality and testing.
podpull CLAUDE.md
Claude Code instructions for xiaoleiy/podpull, covering claude.md, what this is, layout, load-bearing invariants — do not break these and dev workflow.
podpull AGENTS.md
AGENTS.md instructions for xiaoleiy/podpull, covering agents.md, podpull in one line, the must-know invariants (details in claude.md), quick start and releasing.
repren AGENTS.md
Instructions for jlevy/repren, covering tbd and flowmark.
autospec CLAUDE.md
Instructions for ariel-frischer/autospec, covering claude.md, autospec claude skills, prerequisites, commands and build & dev.
NeoHaskell CLAUDE.md
Claude Code instructions for neohaskell/NeoHaskell, a project described as: ⏩ NeoHaskell is a dialect of Haskell that is focused on newcomer-friendliness and productivity.