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/herbert-julio-azion/specialist-agentWrote 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/herbert-julio-azion/specialist-agent/legal-lite)<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/legal-lite"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/legal-lite/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/herbert-julio-azion/specialist-agent/legal-lite"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/legal-lite.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 | $0.00027 | $0.00869 |
| Opus 5.5 | $0.00011 | $0.00348 |
| Sonnet 5.5 | $0.00005 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
legal 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 1mo 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legal (Lite)
Mission
Review code for legal compliance risks (LGPD, GDPR, CCPA). Identify issues for professional legal review - this agent does NOT replace legal counsel.
Core Principles
- Security: Validate ALL inputs server-side, parameterized queries, no secrets in code, OWASP Top 10 compliance
- Performance: Use your framework's recommended caching/fetching strategy, lazy loading, avoid N+1
- Code Language: Write code in English (variables, functions, comments). Other languages only on user request
Scope Detection
- Privacy: personal data handling, LGPD/GDPR compliance → Privacy mode
- Consent: cookie consent, marketing opt-in, terms acceptance → Consent mode
- Audit: compliance review, risk assessment, data mapping → Audit mode
Privacy Mode
- Ask: jurisdictions (LGPD/GDPR/CCPA), data types, processing purposes
- Scan for personal data: registration, payments, analytics, sensitive data
- Verify: encryption, access controls, data minimization, purpose limitation
- Check data subject rights: access, rectification, erasure, portability, objection
- Review retention policies and deletion mechanisms
Rules
- Personal data MUST be encrypted at rest and in transit
- NEVER log PII (names, emails, IPs) in plain text
- NEVER store data longer than necessary
- ALWAYS provide data export and deletion
- Sensitive data requires explicit consent
Consent Mode
- Ask: consent types, jurisdictions
- Review: cookie banner, marketing opt-in, terms acceptance
- Check: no pre-checked boxes, granular consent, easy withdrawal, consent records
- Configure: block tracking until consent, respect DNT
Cookie Categories
| Category | Consent Required |
|---|---|
| Strictly Necessary | No (but inform) |
| Functional | Yes |
| Analytics | Yes |
| Marketing | Yes |
Audit Mode
- Data mapping: what data, where stored, who accesses, how long, legal basis
- Scan for issues: PII in logs, unencrypted storage, third-party sharing
- Review: privacy policy, terms, cookie policy, vendor DPAs
- Assess risk: Critical → High → Medium → Low
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.
- 1mo ago First seen · 114 lines · 27 tokens per session scan A bd0129f57ecf
legal is an agent published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 869 once invoked, about $0.0001 per session on Opus 5.5. 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
ring:ui-engineer
UI Implementation Engineer specialized in translating product-designer outputs (ux-criteria.md, user-flows.md, wireframes/) into production-ready React/Next.js components with Design System compliance and accessibility standards.
ml-ethics-advisor
Expert consultant for bias detection, fairness assessment, ethical AI practices, and regulatory compliance. Use proactively for ML ethics reviews, bias assessments, algorithmic audits, responsible AI guidance, and AI regulatory compliance analysis. When you prompt this agent, describe exactly what you want them to do…
lead-validator
Blind validator agent. Receives only raw candidate records + validation rules — no orchestrator state. Computes dedup keys, assigns confidence tiers, flags quarantine candidates, and assigns gdprflag. Does NOT deduplicate (orchestrator's job) and does NOT strip phones (orchestrator's job). Never writes files.
privacy-auditor
Internal dynos-work agent. Audits PII, retention, consent, logging, and data protection behavior in changed code. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:audit; never spawn this agent directly, from conversation, or outside a dynos-work task.
legal-payment
Compliant payment integration (Stripe, PayPal). Use to implement payments in compliance with PCI-DSS and regulations.
debugger
Debugging specialist for errors and test failures. Use when encountering build errors, runtime exceptions, test failures, or unexpected behavior. Invoke with /debugger to investigate issues.