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/doctormacky/okf-mcp/okf-nl2sqlnpx skills add doctormacky/okf-mcp --skill okf-nl2sqlgit clone --depth 1 https://github.com/doctormacky/okf-mcpWrote 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/doctormacky/okf-mcp/okf-nl2sql)<a href="https://agentmods.dev/skills/doctormacky/okf-mcp/okf-nl2sql"><img src="https://agentmods.dev/badge/skills/doctormacky/okf-mcp/okf-nl2sql.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 | $0.00110 | $0.01297 |
| Opus 5 | $0.00055 | $0.00648 |
| Sonnet 5 | $0.00022 | $0.00259 |
| Haiku 4.5 | $0.00011 | $0.00130 |
Grade A, and why
okf-nl2sql 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 4d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Answer Business Questions With SQL
Use OKF knowledge first, then bounded database discovery only when the knowledge is insufficient. The user supplies business intent, not physical schema names.
Requirements
- Discover the available MCP tools that expose
list_bundles,search_concepts, andget_concept; use the fully qualified names provided by the current host. Do not assume an MCP server namespace. - Before the first CLI call, run
command -v dbexplainanddbexplain --version; require v0.1.11 or newer. Report a missing capability without installing software. - Never read or edit database configuration, request credentials, construct a
command-line DSN, use
--sample, or write to the database or Bundle. - Keep SQL, query plans, physical identifiers, commands, and execution receipts internal. Never expose them in the final answer.
Workflow
Progress:
- Frame the business intent
- Retrieve and ground every required concept
- Build and validate a query plan
- Execute one read-only query
- Verify and report the result
1. Frame Intent
Identify measure, entity, dimensions, time range, filters, and output grain. Ask only about business ambiguity that changes the answer. Never ask the user to choose a table, column, JOIN, dialect, or label.
2. Retrieve Evidence
Read retrieval-and-grounding.md when the first knowledge hit does not uniquely ground every required intent slot. Read full Concepts before using their bindings; compact search summaries are discovery results, not SQL evidence.
When a Saved Query matches the business intent, use its full Concept as mature SQL evidence while assembling the current query. It does not bypass Metrics, Policies, grain checks, parameter clarification, or final execution.
Prefer existing Bundle evidence. If required physical facts are absent or stale, read live-database-discovery.md. If no executable or semantic relationship exists and an inferred candidate is needed, read inferred-join-validation.md.
What ships with it
7 files 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.
- 4d ago First seen · 127 lines · 110 tokens per session scan A 0688e3519ce9
okf-nl2sql is a skill published in the GitHub repository doctormacky/okf-mcp (1 stars, last pushed today), licensed MIT. It adds 110 tokens to every session and 1,297 once invoked, about $0.0006 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
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
debugging
How to debug tursodb using Bytecode comparison, logging, ThreadSanitizer, deterministic simulation, and corruption analysis tools.
sdk-design
Doctrine for designing and evolving any SDK Grida ships — TypeScript, Rust, or otherwise. "SDK" here means a surface that crosses a foreign-or-foreign-treated boundary: published packages, separately-versioned consumers, FFI bindings, public-by-design modules. An SDK's job is to refuse; a strict, honest surface…
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…