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 looker-open-source/looker-skills --skill looker-performance-optimizergit clone --depth 1 https://github.com/looker-open-source/looker-skillsWrote 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/looker-open-source/looker-skills/looker-performance-optimizer)<a href="https://agentmods.dev/skills/looker-open-source/looker-skills/looker-performance-optimizer"><img src="https://agentmods.dev/badge/skills/looker-open-source/looker-skills/looker-performance-optimizer/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/looker-open-source/looker-skills/looker-performance-optimizer"><img src="https://agentmods.dev/badge/skills/looker-open-source/looker-skills/looker-performance-optimizer.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 | $0.00040 | $0.02463 |
| Opus 5 | $0.00020 | $0.01231 |
| Sonnet 5 | $0.00008 | $0.00493 |
| Haiku 4.5 | $0.00004 | $0.00246 |
Grade A, and why
looker-performance-optimizer 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Looker Performance Optimizer
This master developer skill governs the lifecycle of auditing, diagnosing, and optimizing query performance in new or existing Looker projects. It enforces a strict performance-first design, database caching alignment, strategic data materialization, and advanced SQL profiling using parallel subagents and Looker MCP tools.
All optimizations developed under this skill must be dialect-agnostic, database-efficient, and preserve the integrity of existing business logic.
1. Operating Modes (Preventative vs. Reactive)
This skill operates in two distinct modes to address performance at different stages of the development lifecycle:
Mode A: Performance-by-Design (Preventative Engineering)
Use this mode when adding new explores, views, or Persistent Derived Tables (PDTs) to an existing project. The agent MUST ensure that performance is engineered from the first second:
- Correct Join Cardinalities: Declare precise join relationships (
many_to_one,one_to_one) immediately to prevent compiler-driven Symmetric Aggregations. - PDT Indexing & Partitioning: Every new PDT definition MUST declare partition keys and clustering/index keys based on the fields most commonly used as dashboard filters.
- ETL-Aligned Caching: Every new explore MUST be assigned to a centralized
datagrouptriggered by an ETL/ELT metadata query, avoiding arbitrarypersist_fortime windows.
Mode B: Active Performance Tuning (Reactive Brownfield)
Use this mode when diagnosing and optimizing an active, slow dashboard or explore in production. The agent MUST execute this 5-phase performance pipeline:
- Aesthetic Audit & Baseline: Switch to Developer Mode and run a baseline test of the slow dashboard tiles via Looker MCP or CLI. Record query run times, query IDs, and database costs (bytes scanned/slots used).
- Parallel Query Profiling (Subagent-Assisted): Spawn specialized subagents to analyze the generated SQL and run
EXPLAINplans concurrently, isolating the database bottlenecks (see Section 6 for delegation rules). - Surgical Performance Refactoring: Apply targeted, localized edits to the LookML layer:
- Align caching datagroups.
- Materialize heavy transformations into PDTs (following the PDT Decision Matrix).
- Correct join relationships and implement join pruning.
- Verification & Delta Measurement: Re-run the compiler (
health_analyze) to ensure zero syntax errors, re-execute the queries, and document the performance improvement matrix. - Safe Production Deploy: Deploy the optimized, validated LookML branch to production.
What ships with it
5 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.
- 10d ago First seen · 124 lines · 40 tokens per session scan A 76edd043759f
looker-performance-optimizer is a skill published in the GitHub repository looker-open-source/looker-skills (28 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 2,463 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…