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 skills/vinix24/vnx-orchestration/intelligence-engineernpx skills add Vinix24/vnx-orchestration --skill intelligence-engineergit clone --depth 1 https://github.com/Vinix24/vnx-orchestrationWrote 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/vinix24/vnx-orchestration/intelligence-engineer)<a href="https://agentmods.dev/skills/vinix24/vnx-orchestration/intelligence-engineer"><img src="https://agentmods.dev/badge/skills/vinix24/vnx-orchestration/intelligence-engineer.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 | $0.00000 | $0.03548 |
| Opus 5 | $0.00000 | $0.01774 |
| Sonnet 5 | $0.00000 | $0.00710 |
| Haiku 4.5 | $0.00000 | $0.00355 |
Grade A, and why
intelligence-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intelligence Engineer
VNX-specific domain expert for the intelligence system, central state, and dispatch lifecycle.
Core Mission
VNX has a sprawling but specific data model: dispatches flow through a runtime coordination DB, generate receipts and events, get archived, and feed back into a quality intelligence DB that informs future dispatch decisions. Most "intelligence not working" or "central state weird" bugs are NOT generic database bugs — they're domain bugs in VNX-specific code paths.
This skill exists alongside database-engineer (which covers SQLite mechanics generically). Use database-engineer for migration/schema/UPSERT work; use this skill when the question requires knowing which VNX table holds what, and why.
When to Use
- Editing or designing schemas in
schemas/quality_intelligence.sql,schemas/runtime_coordination_v*.sql, or any0010_…/0015_…migration - Touching
scripts/quality_db_init.py,scripts/lib/coordination_db.py, or any module that initializes / queries central state - Working with intelligence injection:
scripts/lib/intelligence_*,scripts/build_t0_state.py,scripts/lib/intelligence_injection.py - Debugging "code_snippets show wrong project", "dispatches missing from T0 state", "success_patterns not retrieved", "central DB query returns nothing"
- Querying central DB for cross-project insights (federation, aggregation, analytics)
- Designing a new intelligence-feeding mechanism (e.g. new event type → injection rule)
- Modifying any code that touches the project_id flow (registry → import → query → injection)
STEP 0 — Foundational Check (Mandatory)
BEFORE proposing any design, fix, or implementation:
- Consult relevant ADRs in
docs/governance/decisions/. Special attention to:- ADR-005 (NDJSON audit ledger as primary observability)
- ADR-007 (multi-tenant project_id stamping; composite keys for central state DBs)
- ADR-010 (subprocess adapter as canonical Claude routing) List any ADR that applies to the task and how it constrains your solution.
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 · 245 lines · 0 tokens per session scan A c5d328f683e9
intelligence-engineer is a skill published in the GitHub repository Vinix24/vnx-orchestration (57 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,548 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 2026-08-30.
Other skills, from other repositories
database-patterns
Database design and implementation patterns for modern applications. Use when designing schemas, writing migrations, optimizing queries, and configuring ORMs. Covers PostgreSQL, MongoDB, Prisma, Drizzle, indexing strategies, and security best practices.
oma-db
Database specialist for SQL, NoSQL, and vector database modeling, schema design, normalization, indexing, transactions, integrity, concurrency control, backup, capacity planning, data standards, anti-pattern review, and compliance-aware database design. Use for database, schema, ERD, table design, document model…
agent-teams
Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.
sql_query
当用户提出数据查询需求（如'查数'、'查一下订单量'、'有多少用户'、'帮我跑个SQL'等），使用数据源工具发现表结构，生成并执行只读 SQL 查询。.
migration-ready-schema
Data-model rules that make a schema importable from day one, so the migration-import-engineer is never blocked on missing columns. Every SMB Product-Builder product must let a customer bring their data from an incumbent (ServiceTitan/Toast/Mindbody/Shopify) — that requires provenance (sourceref) and rollback…
continuum-memory
Configure and use Continuum's two-tier memory system — mem0+Qdrant/Milvus for long-term facts, Redis for short-term sessions, with multi-tenant scopes (USER / AGENT / SHARED / RUN / CONVERSATION). Invoke when the user asks about "remember", "user preferences", "long-term memory", "vector search over memories"…