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 skills add CassioRoos/godfly-skills --skill devils-advocategit clone --depth 1 https://github.com/CassioRoos/godfly-skillsWrote 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/skills/cassioroos/godfly-skills/devils-advocate)<a href="https://agentmods.dev/skills/cassioroos/godfly-skills/devils-advocate"><img src="https://agentmods.dev/badge/skills/cassioroos/godfly-skills/devils-advocate.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 | $0.00109 | $0.01137 |
| Opus 5 | $0.00055 | $0.00568 |
| Sonnet 5 | $0.00022 | $0.00227 |
| Haiku 4.5 | $0.00011 | $0.00114 |
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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devil's Advocate - Opposing Counsel
A decision is about to be made. Your job is to argue the other side like you actually believe it. Not to nitpick the chosen path - to build the strongest possible case that the alternative is right, or that the decision shouldn't happen at all. Better to hear the opposition in the lab than from reality in production.
Core Principle
Steelman the alternative, don't strawman it. A devil's advocate who argues half-heartedly is worse than none - it inoculates the decision against real opposition without testing it. Argue as if you were paid to win.
The Opposing-Brief Protocol
1. State the Position Being Opposed
One sentence. Name the decision, the chosen path, and what it's being chosen over.
"The team is about to migrate the billing service to event sourcing instead of keeping the current CRUD model."
If you can't state it in one sentence, the decision isn't crisp enough to oppose - sharpen it first.
2. Build the Brief
Argue for the other side across four fronts:
- Attack the load-bearing assumptions. Every decision rests on a few claims that, if false, collapse the whole case. Name them explicitly and argue why each could be wrong. Not the peripheral assumptions - the ones the decision cannot survive without.
- Present the alternative's genuine benefits. What does the rejected path actually do well? Argue its merits as its best advocate would - concrete benefits, not faint praise. If the alternative is "do nothing," argue the real value of the status quo: stability, optionality, resources freed for other bets.
- Name the costs and irreversibilities of the chosen path. What does this decision spend that can't be recovered - time, money, credibility, architectural flexibility? Which doors does it close? One-way doors deserve far harder opposition than two-way doors.
- State the conditions under which the opposition wins. Under what circumstances does the alternative turn out to be right? Be specific: "If migration takes longer than one quarter," "if the vendor raises prices," "if the team loses its one event-sourcing expert." These are the scenarios where this brief becomes prophecy.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 77 lines · 109 tokens per session scan A 8c5a56f2e4c4
devils-advocate is a skill published in the GitHub repository CassioRoos/godfly-skills (1 stars, last pushed 7d ago), licensed MIT. It adds 109 tokens to every session and 1,137 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
remove-ai-marks
Strip multi-vendor AI provenance from owned files: hidden Unicode (Layer A), statistical sampling watermarks via rewrite (Layer B — always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Covers Claude, Gemini/SynthID-class, OpenAI provenance surfaces, and open-LLM sampling…
clean-user-facing-text
Audit and finalize authorized natural-language text meant for readers: strip suspicious invisible Unicode, then rewrite prose while keeping facts, meaning, and the writer's voice. Use when the user asks to clean, humanize, polish, or finalize articles, manuscripts, reports, documentation, emails, product copy, UI…
html-portal-generator
Convert a codebase into a self-contained HTML portal app for ingestion into AI application systems. Produces a single deployable HTML file with embedded CSS, JS, and data.
bensz-rmd-rules
A set of rules for creating R Markdown analysis scripts. R Markdown combines written explanation, R code, calculations, and results in one document.
auto-test-code
A structured process for critically reviewing and testing software code. It records review findings, test plans, commands, results, and supporting files in a project workspace.
auto-test-skill
A structured process for critically testing and improving a coding skill. It records test plans, findings, fixes, and quality checks in files that can be reviewed later.