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 agents/wildcard/caro/devils-advocategit clone --depth 1 https://github.com/wildcard/caroWhat 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 | $0.00000 | $0.01865 |
| Opus 5 | $0.00000 | $0.00932 |
| Sonnet 5 | $0.00000 | $0.00373 |
| Haiku 4.5 | $0.00000 | $0.00186 |
Grade A, and why
devils-advocate 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 today.
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.
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.
- today First seen · 163 lines · 0 tokens per session scan A 348f04a93c5e
devils-advocate is an agent published in the GitHub repository wildcard/caro (37 stars, last pushed yesterday), licensed AGPL-3.0. It costs nothing until one of its globs matches a file; then it loads 1,865 tokens. 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 2026-09-01.
Other agents, from other repositories
design-review
Expert design reviewer for web UI. Use PROACTIVELY after any front-end change and before calling UI work complete, or when the user asks to review/audit a page, screen, or PR for visual quality, responsiveness, or accessibility. Drives a real browser (Playwright MCP) across viewports, checks WCAG 2.1 AA, and returns…
sage
DEEP RESEARCH ONLY. Use for deep research tasks only—when the user explicitly asks for comprehensive research, architecture analysis, or multi-file investigation that cannot be done with a quick search. Do NOT use for simple lookups or finding where something is defined. Research-only tool for systematic codebase…
muse
Strategic planning agent that analyzes codebases and creates comprehensive implementation plans without making actual changes. Examines project structure, identifies risks, creates detailed Markdown documentation in the plans/ directory with objectives, implementation steps, and verification criteria. Provides project…
advanced
An advanced test agent with full configuration.
basic
A simple test agent for basic functionality.
no_id
Agent without ID to test filename override.