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 contactandrewchl-wq/turtle-mcp --skill backend-performancegit clone --depth 1 https://github.com/contactandrewchl-wq/turtle-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/contactandrewchl-wq/turtle-mcp/backend-performance)<a href="https://agentmods.dev/skills/contactandrewchl-wq/turtle-mcp/backend-performance"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/backend-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/contactandrewchl-wq/turtle-mcp/backend-performance"><img src="https://agentmods.dev/badge/skills/contactandrewchl-wq/turtle-mcp/backend-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 | $0.00051 | $0.00986 |
| Opus 5 | $0.00026 | $0.00493 |
| Sonnet 5 | $0.00010 | $0.00197 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
backend-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 10d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend performance
Cuándo usar
- Latencia o throughput por debajo del SLO.
- Endpoint nuevo en ruta crítica.
- Antes de un evento de tráfico alto.
No cargar para optimizaciones especulativas sin medición.
Disciplina
- Medí primero. Sin perfil, no hay diagnóstico, hay opinión.
- Optimizá el cuello. Mejorar lo que ya es rápido es trabajo perdido.
- Comprobá el efecto. Si no medís después, no sabés si ayudó.
Mediciones base
- Latencia p50/p95/p99 por endpoint.
- Throughput (req/s) sostenido sin degradar.
- Recursos: CPU, memoria, IO, conexiones a BD, cola.
- Distribución: ¿es lento siempre o por colas? Histograma > promedio.
Herramientas
| Capa | Herramienta |
|---|---|
| CPU/IO/lock | perf, pprof, py-spy, clinic.js, async-profiler |
| Queries | EXPLAIN ANALYZE, pg_stat_statements, slow query log |
| Trazas | OpenTelemetry + Jaeger/Tempo (ver [[backend-observability]]) |
| HTTP | k6, vegeta, wrk para carga |
| Memoria | heap dump + analizador del runtime |
Patrones que suelen pagar
Base de datos (suele ser el 80%)
- N+1 → eager loading / JOIN. Detectá con conteo de queries por request.
- Índice faltante en
WHERE/JOIN/ORDER BYfrecuente.EXPLAINpara confirmar uso. SELECT *→ seleccioná solo lo que usás (menos IO, menos transferencia).- Pool de conexiones del tamaño correcto (no infinito).
(núcleos * 2) + spindleses una base. - Read replicas para queries pesadas de lectura, si la consistencia eventual sirve.
Caché
Niveles, del más barato al más caro:
- Memoization del proceso — para cálculos puros, invalida con LRU.
- Caché distribuida (Redis) — para datos compartidos. TTL razonable.
- CDN / edge — para respuestas idempotentes públicas.
Toda caché necesita estrategia de invalidación. Sin esa, es bug en cámara lenta.
Cache stampede → single-flight o lock corto.
Batching y bulk
- Operaciones en N items en una sola query, no N queries.
INSERT ... VALUES (...), (...), (...)oCOPYen Postgres.- Para HTTP: agrupá calls a APIs externas en uno cuando lo permite.
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.
- 10d ago First seen · 102 lines · 51 tokens per session scan A 702168fd0a2b
backend-performance is a skill published in the GitHub repository contactandrewchl-wq/turtle-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 986 once invoked, about $0.0003 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
simplicio-dev-cli
Perform deterministic Simplicio code changes and validation through the Dev CLI. Use for file edits, patches, implementation, formatting, tests, diagnostics, pre-effect validation, retries, evidence files, and safe mutation workflows. The agent decides intent; Dev CLI owns the mutation and verification.
optimization
Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
groq-inference
Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
bun-file-io
Use this when you are working on file operations like reading, writing, scanning, or deleting files. It summarizes the preferred file APIs and patterns used in this repo. It also notes when to use filesystem helpers for directories.