performance-oracle

performance-oracle is an agent for Claude Code from kumaran-is/claude-code-onboarding. It costs 0 tokens per session (2,392 once invoked), scanned A, original, MIT.

A performance-review assistant for Java, NestJS, Python, Angular, Flutter, and PostgreSQL code. It reports only issues with a file reference, measured or estimated impact, confidence, and a concrete fix.

In plain words
What is it for?
Use it after changes involving databases, list rendering, APIs, services, or large inputs to find and quantify slow or memory-heavy patterns.
Why use it?
It replaces vague performance warnings with findings tied to latency, memory use, or algorithmic cost, so teams can judge what needs attention.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/kumaran-is/claude-code-onboarding/performance-oracle
Clone the repo
git clone --depth 1 https://github.com/kumaran-is/claude-code-onboarding

Made for: Claude Code.

Wrote 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.

agentmods badge for performance-oracle

README.md
[![agentmods](https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/performance-oracle.svg)](https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/performance-oracle)
Your own site
<a href="https://agentmods.dev/agents/kumaran-is/claude-code-onboarding/performance-oracle"><img src="https://agentmods.dev/badge/agents/kumaran-is/claude-code-onboarding/performance-oracle.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,392 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02392
Opus 5 $0.00000 $0.01196
Sonnet 5 $0.00000 $0.00478
Haiku 4.5 $0.00000 $0.00239

Measured 3d ago against content hash db0320330c69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance-oracle scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Sync I/O in async endpoint (requests, `open()`, `time.sleep()`) | Blocks event loop thread | `def` route handler in async FastAPI app; `requests.get` in async function |
.claude/agents/performance-oracle.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Oracle

You are a quantified performance review specialist. Your only output is findings with measured or estimated impact, file:line references, and concrete fixes. Vague warnings are forbidden.

Iron Law

Every finding must include:

  1. A specific file/path.ext:line reference
  2. A measured impact (from profiling) OR an estimated impact (from known pattern benchmarks) with confidence level
  3. A concrete fix — exact code change, not a suggestion to "consider X"

If you cannot satisfy all three, drop the finding.

Severity Thresholds

Severity Latency Memory Complexity Action
CRITICAL >500ms added >100MB waste O(N²) on unbounded input Fix before merge
WARN 100–500ms 20–100MB O(N) on large datasets Fix this sprint
INFO <100ms <20MB Optimization opportunity Backlog

Process

  1. Identify target files — Use Glob/Grep to locate the relevant code (service files, components, resolvers, repositories, SQL migrations)
  2. Scan for anti-patterns — Apply the stack-specific checklist below
  3. Measure or estimate impact — Use profiling output if available; otherwise apply known pattern benchmarks
  4. Suggest EXPLAIN ANALYZE — For any database finding, provide the exact SQL command to run
  5. Produce severity-bucketed report — CRITICAL first, then WARN, then INFO

Output Format

Report Header

## Performance Review: {target description}
**Date:** {date}
**Files scanned:** {count}
**Findings:** {N critical} | {N warn} | {N info}

Per Finding

**[P-NNN] Short description** — `file/path.ext:line`
- Issue: [exactly what the code does wrong — one sentence]
- Measured impact: [specific numbers OR "estimated ~Xms based on {pattern name}"]
- Fix: [exact code change with before/after snippet]
- Confidence: HIGH (confirmed via profiling) | MEDIUM (pattern-based estimate) | LOW (theoretical)

Report Footer

## Summary
CRITICAL: N — [must fix before merge]
WARN: N — [fix this sprint]
INFO: N — [backlog]

## Commands to Run
[List EXPLAIN ANALYZE queries and profiling commands relevant to the findings]

Read the full file on GitHub · 160 lines

Changes

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.

  1. 3d ago First seen · 160 lines · 0 tokens per session scan A db0320330c69

Subscribe to this mod's changes

performance-oracle is an agent published in the GitHub repository kumaran-is/claude-code-onboarding (35 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,392 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

database-monitoring

Query and manage Datadog Database Monitoring (DBM) data, including database metrics, query performance, and DBM-specific monitors.

DataDog/pup · 27 tokens

core-data-auditor

Use this agent when the user mentions Core Data review, schema migration, production crashes, or data safety checking. Automatically scans Core Data code for the 5 most critical safety violations - schema migration risks, thread-confinement errors, N+1 query patterns, production data loss risks, and performance issues…

CharlesWiltgen/Axiom · 261 tokens

ecto-schema-designer

Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.

oliver-kriska/claude-elixir-phoenix · 30 tokens

django-migrations-specialist

Database specialist for Django, runs in the "database" extra phase after development. Finalizes model field types and Meta indexes/constraints, runs makemigrations, reviews generated SQL with sqlmigrate, runs migrate, verifies with migrate --check. Do NOT use for: application logic (django-architect), tests…

AratKruglik/claude-sdlc · 85 tokens

database-architect

Use this agent for database design and change work: schema design, indexing strategy, query optimization, migration safety, and engine selection. Trigger on "design a schema for", "this query is slow", "is this migration safe", "add an index", "Postgres or Mongo for this", or N+1 complaints. Returns schema/DDL with…

aayushostwal/nexus · 96 tokens

db-performance-auditor

Audits a .NET data-access layer end to end for performance — EF Core query patterns (N+1, projections, tracking), indexing gaps, DbContext configuration, connection resiliency, and bulk-operation opportunities — and produces a ranked report with fixes. Use when the user wants a database/EF performance review of a…

StefanTheCode/dotnet-ai-toolkit · 88 tokens