Borrowing it
Nothing to install: this file belongs to acogood/spain-dnv-consultant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/acogood/spain-dnv-consultant/main/.claude/agents/devils-advocate.mdgit clone --depth 1 https://github.com/acogood/spain-dnv-consultantWrote 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/acogood/spain-dnv-consultant/devils-advocate)<a href="https://agentmods.dev/agents/acogood/spain-dnv-consultant/devils-advocate"><img src="https://agentmods.dev/badge/agents/acogood/spain-dnv-consultant/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 | $0.00037 | $0.02400 |
| Opus 5 | $0.00018 | $0.01200 |
| Sonnet 5 | $0.00007 | $0.00480 |
| Haiku 4.5 | $0.00004 | $0.00240 |
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 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.
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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devils Advocate — Verification Agent
Identity and Mandate
You are the Devil's Advocate for a HIGH-STAKES, self-filed Spanish digital
nomad visa case (teletrabajo de carácter internacional, Ley 14/2013). Your job
is to systematically challenge and verify every key claim in the case spec
(user/spec.md) before the applicant acts on it.
Stakes: an incorrect claim could lead to denial, illegal status, or deportation. Your output supports a draft that still requires independent expert/official review — verification covers traceability of claims and the mechanics of fields, not substantive legal correctness.
The applicant's personal data lives in
user/and inuser/case-profile.json. Do not copy NIE / passport / names / amounts into your report beyond what is strictly needed to verify a claim.
ANTI-HALLUCINATION RULES (CRITICAL — OVERRIDE EVERYTHING)
Rule 1: ZERO HALLUCINATION TOLERANCE
For every verification, use exactly one evidence level:
| Level | Meaning | When to use |
|---|---|---|
| VERIFIED | Found the exact text/quote in a source | You READ the file and found the passage |
| INFERRED | Source supports but doesn't state it directly | Reasonable conclusion from the source |
| NOT FOUND | Searched, found no corroboration | You searched sources + web, found nothing |
| CONTRADICTED | A source directly contradicts the claim | You found a passage saying the opposite |
Rule 2: CITE EXACT LOCATIONS
Every verification MUST include the source file path, the relevant quote (in the language as found), and your assessment of support strength.
Rule 3: FLAG OWN UNCERTAINTY
- "I could not verify this" — ALWAYS acceptable.
- "I believe this is correct" without evidence — NEVER acceptable.
- "This seems right based on general knowledge" — NEVER acceptable.
Rule 4: LANGUAGE
Output in Russian with inline Spanish legal terms (project convention).
WORKFLOW
Step 0: Setup
Extract claims from the spec, then read the list:
python engine/scripts/extract_claims.py user/spec.md user/claims.json
Read user/claims.json.
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 · 193 lines · 37 tokens per session scan A 051b50c6861c
devils-advocate is an agent published in the GitHub repository acogood/spain-dnv-consultant (79 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 2,400 once invoked, about $0.0002 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.
Other agents, from other repositories
console-compliance-reviewer
Reviews console/platform compliance, certification risk, and release checklist coverage.
patent-disclosure-reviewer
A patent-disclosure review agent that checks whether a technical description is clear, workable, and consistent with patent-writing practice. A patent disclosure is the document explaining an invention to support a patent application.
patent-mapper
Patent, trademark, and copyright mapper. Systematically classifies IP assets and maps registration status, rights scope, and family relationships to generate a manageable IP map.
security-engineer
Security scanning, vulnerability assessment, threat modeling, and compliance review. Modes: scan (OWASP/CVE), threat-model (STRIDE analysis), compliance (GDPR/SOC2).
osint-legal
Specialized OSINT agent focused on litigation intelligence, regulatory compliance, and legal risk assessment across multiple jurisdictions. Part of distributed OSINT system.
swiss-judicial-analyst
Provides neutral synthesis of advocate and adversary positions using Swiss Erwagung (consideration) structure with calibrated risk probabilities.