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 joao-aires/agent-skills-public --skill database-performancegit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/database-performance)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/database-performance"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/database-performance/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/joao-aires/agent-skills-public/database-performance"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/database-performance.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 | $0.00038 | $0.00573 |
| Opus 5.5 | $0.00015 | $0.00229 |
| Sonnet 5.5 | $0.00008 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
database-performance 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 yesterday.
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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve the measured workload
Establish the affected user operation, target, data distribution, load/concurrency and execution environment. Reuse existing service objectives. Distinguish a single query's elapsed time from request latency, queueing, lock/pool wait, serialization, network transfer and downstream work. Ask for missing performance commitments only when the decision depends on them; keep estimates labelled.
Diagnose before prescribing
Locate the time spent in the affected user operation before tuning a query. Separate waiting for a connection, waiting for another transaction, executing SQL, transferring results and processing them in the application. Improving the query plan will not necessarily help a request whose time is spent waiting elsewhere.
Use aggregate workload evidence to choose which operations matter. A frequently executed moderate query can consume more resources than an occasional slow one; a severe tail can still make a critical journey unusable. Compare those costs with the accepted user outcome, then form a specific explanation to test.
- Inspect representative plans, cardinalities, waits and resource pressure with matching technical expertise.
- Separate cold/warm behavior and tenant/data-size slices where they affect the conclusion.
- Estimated plan costs are not wall-clock measurements, and a scan or a particular join type is not inherently a defect.
Treat production diagnostics as workload with an impact. Confirm the target, access and permitted load; use existing traces or non-executing plans when sufficient.
A plan that runs the statement can change data or impose substantial load, and rollback does not reverse every external effect. Keep sensitive query parameters and records out of reports.
Compare changes against the full contract
Form a testable bottleneck hypothesis. Consider the query/access pattern, data representation, indexes/statistics, connection behavior and resource limits before adding infrastructure. Choose discriminating changes and record enough conditions to attribute the outcome. An index can improve reads while worsening write latency, storage and maintenance; caches and replicas introduce staleness and failure behavior.
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.
- yesterday First seen · 43 lines · 38 tokens per session scan A 3281bc066751
database-performance is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 573 once invoked, about $0.0002 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 2026-10-21.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
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.
atlas-mssql
SQL Server specifics for Atlas (also Azure SQL and MSSQL): login, dev database and URL scope (mode=schema vs mode=database, the database query parameter), compatibility level and collation, system-generated constraint names, clustered index defaults and datetime2 precision in HCL, GO batches and the delimiter…
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…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
volcengine-rds-postgresql
A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.