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 skills add kreek/consult --skill databasegit clone --depth 1 https://github.com/kreek/consultWrote 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/kreek/consult/database)<a href="https://agentmods.dev/skills/kreek/consult/database"><img src="https://agentmods.dev/badge/skills/kreek/consult/database/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/skills/kreek/consult/database"><img src="https://agentmods.dev/badge/skills/kreek/consult/database.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 | $0.00022 | $0.00912 |
| Opus 5.5 | $0.00009 | $0.00365 |
| Sonnet 5.5 | $0.00004 | $0.00182 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
database 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 16d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database
Iron Law
PROTECT PRODUCTION DATA FIRST: PROVE ROLLOUT, LOCKING, AND RECOVERY BEFORE CHANGE.
When to Use
- Schema design, migrations, indexes, query plans, isolation levels, connection pools, soft delete, N+1 fixes, online DDL, transactional outbox/CDC, or production data changes.
When NOT to Use
- API contract design; use
api. - Rollout sequencing outside the database; pair with
release. - Cache freshness and invalidation; use
performance.
Rules
- Destructive and hard-to-reverse database changes are the user's call.
Schema and migration changes that other code or stored data binds to route
through
contract-first, which owns the approval scope. Data deletion and non-reversible backfills always need explicit approval, because a rollback cannot undo them. An additive, easily reversed change on a development-stage schema proceeds with its shape stated in the close-out. - Use the project's existing database unless the task is choosing a store;
architectureowns store selection. - Destructive or tightening changes ship as separate deployable expand-contract phases: expand, migrate, verify, switch, contract.
- Review the migration SQL and its lock behavior directly, not just the ORM code. Index and constraint creation uses the target engine's online mechanism. SQLite passing is not proof of Postgres behavior; verify engine-specific DDL against the target engine.
- Every uniqueness invariant is enforced by a DB-level
UNIQUE,EXCLUDE, composite, or partial constraint, because application-layer checks race under concurrency. - New foreign keys and known
WHERE,JOIN, orORDER BYpredicates get supporting indexes in the same migration, or a stated reason they do not. Important query changes include EXPLAIN/ANALYZE on production-shaped data. - Backfills are batched, resumable, observable, and reversible, and each batch holds locks briefly.
- Isolation level and retry behavior are explicit for transactional changes. State changes and durable publication (events, jobs) share a transactional outbox, CDC, or equivalent when the two must not silently diverge.
- Rollback and backup/PITR coverage for the blast radius are documented with the change.
What ships with it
3 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.
- 16d ago Changed · +3 tokens per session 70c8856d50d5
- 1mo ago Changed · -40 lines 4e12909f7e5e
- 1mo ago First seen · 120 lines · 19 tokens per session scan A fdd3bdf404f1
database is a skill published in the GitHub repository kreek/consult (1 stars, last pushed 17d ago), licensed MIT. It adds 22 tokens to every session and 912 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 2026-08-31.
Other skills, from other repositories
swiftdata-workflow
Design, implement, migrate, test, and integrate SwiftData persistence in Apple apps using current Apple documentation. Use for @Model schemas, ModelContainer and ModelContext ownership, @Query integration, relationships, uniqueness, deletion, concurrency, migrations, preview or test stores, and boundaries between…
ggsql
Write ggsql queries — a grammar of graphics for SQL. Use when the user wants to create, modify, or understand a ggsql visualization query.
phoenix-contexts
Phoenix context design — creating/splitting contexts, Scope (1.8+), Ecto.Multi, PubSub, routers, plugs, controllers. Use when editing contexts, routers, or designing boundaries.
ecto-n1-check
Detect N+1 query anti-patterns specifically — Repo calls inside Enum/for loops, missing preloads on associations. Use when N+1 is explicitly suspected, NOT for unrelated Ecto questions or wider database performance.
constraint-debug
Compatibility alias for the Elixir/Phoenix plugin's Ecto constraint debugger. Invoke explicitly with /ecto:constraint-debug.
n1-check
Compatibility alias for the Elixir/Phoenix plugin's N+1 query checker. Invoke explicitly with /ecto:n1-check.