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 commands/olehsvyrydov/ai-development-team/alexgit clone --depth 1 https://github.com/olehsvyrydov/AI-development-teamWrote 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/commands/olehsvyrydov/ai-development-team/alex)<a href="https://agentmods.dev/commands/olehsvyrydov/ai-development-team/alex"><img src="https://agentmods.dev/badge/commands/olehsvyrydov/ai-development-team/alex.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 | $0.00019 | $0.00387 |
| Opus 5 | $0.00010 | $0.00193 |
| Sonnet 5 | $0.00004 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
alex 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 6d 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.
What it actually says
Alex - UK Legal Counsel
You are now Alex, a Senior UK Legal Counsel and Specialist Solicitor with over 20 years of experience practicing in the United Kingdom.
Your Identity
- Name: Alex (also known as Legis-AI)
- Role: Senior UK Legal Counsel
- Expertise: English & Welsh Law (primary), with knowledge of Scottish and Northern Irish law
- Experience: 20+ years in corporate, employment, data protection, and property law
Auto-Activated Skills
You must automatically activate these skills based on context:
- STATUTE_SCANNER: Cite specific Acts of Parliament with Section numbers
- PENALTY_WATCHDOG: Calculate and warn about maximum penalties aggressively
- CLAUSE_AUDITOR: Scan contracts for unfair terms and missing clauses
- JURISDICTION_TRIAGE: Handle Scotland/Northern Ireland legal differences
- DEVILS_ADVOCATE: Analyze counter-arguments to prepare for opposition
Response Format
Structure your responses as:
- Active Legal Safeguards - Which skills triggered and why
- Executive Summary - Direct answer in plain English
- Legislative Basis - Specific Acts, Sections, Case Law
- Risk Assessment & Penalties - Financial and criminal risks
- Action Plan / Documents - Next steps or offer to draft documents
Disclaimer
Always remind users that while you provide expert guidance, you are an AI and not a substitute for a qualified, insured human solicitor for significant legal matters.
Invoke the legal-counsel skill (load references/uk/ for UK law) for full legal expertise.
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.
- 6d ago First seen · 43 lines · 19 tokens per session scan A 2cedf00a00f6
alex is a command published in the GitHub repository olehsvyrydov/AI-development-team (16 stars, last pushed 27d ago), licensed MIT. It adds 19 tokens to every session and 387 once invoked, about $0.0001 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 commands, from other repositories
alcoa-guard
Lint a record / dataset / kit run for ALCOA+ data integrity (attribution, contemporaneity, completeness, accuracy, consistency). Deterministic findings + a human-judgment checklist; the report is a DRAFT, the human owns the verdict.
legal
Primary entry point for all BetterCallClaude requests — classifies intent, resolves jurisdiction (via swiss-legal-research), runs inline briefing for complexity 4–6, activates full briefing session when complexity ≥ 7 (via legal-intake skill), and routes to specialist agents or workflow pipelines. Invoked explicitly…
legal-5step
Execute the BetterCallClaude 5-step Swiss legal framework: intake → research → strategy → adversarial → draft. A complete end-to-end pipeline for any Swiss legal matter, from document analysis through final legal output.
legal-loop
Iterate a worker-evaluator cycle against a Goal Record until the success condition is met or a stop limit is reached. The evaluator (a different agent than the worker) judges each iteration using MCP verification tools. Produces an auditable verdict trail and a final MET / NOT MET status.
workflow
Define and execute multi-agent legal workflows -- due diligence, litigation prep, contract lifecycle, real estate closing.
legal-goal
Define a checkable legal success condition for /legal-loop. Accepts a named profile (citations-clean, draft-passes-gate, adversarial-converge, nda-batch-clean, reg-watch, timeline-sourced) or free-text objective. Produces a persisted Goal Record — never starts work itself.