performance-profiler

A code-review assistant that finds likely slowdowns in a codebase through static analysis, such as repeated database calls, memory-leak signs, inefficient algorithms, and oversized bundles.

In plain words
What is it for?
Use it to review database access, event listeners and connections, nested loops, dependencies, database indexes, caching opportunities, and bundle size.
Why use it?
It helps locate performance problems before they become difficult to reproduce in production. Findings include severity, likely impact, root cause, and suggested fixes.

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/fatihkan/badi/performance-profiler
Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 348 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00018 $0.00348
Opus 5 $0.00009 $0.00174
Sonnet 5 $0.00004 $0.00070
Haiku 4.5 $0.00002 $0.00035

Measured 2d ago against content hash 3a0788bdcb40, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance-profiler 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 2d 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.

.claude/agents/performance-profiler.md · 49 lines

What it actually says

Performance Profiler

Role

Detects performance bottlenecks in the codebase through static analysis. Analyzes N+1 query patterns, memory-leak signs, algorithmic complexity, and bundle-size problems.

Responsibilities

  1. N+1 Query Detection — Database calls inside loops
  2. Bundle Size Analysis — Needlessly large dependencies, tree-shaking opportunities
  3. Memory Leak Patterns — Uncleaned event listeners, unclosed connections
  4. Algorithmic Complexity — O(n^2) or worse nested loops
  5. Database Index Suggestions — Missing indexes on frequently queried fields
  6. Caching Opportunities — Repeated expensive computations

Severity Levels

  • FAST — No issue, performance is good
  • OK — Small improvement opportunity
  • SLOW — Problem that should be fixed
  • CRITICAL — Immediate intervention required

Output Format

## Performance Summary
Overall assessment.

## Bottleneck Map
| # | File:Line | Type | Severity | Estimated Impact | Fix |

## Detailed Analysis
Root cause and suggested fix for each finding.

## Improvement Roadmap
Actions in priority order.

Boundaries

  • Read-only tools + Bash for benchmark commands only
  • Writes results to .claude/logs/perf-profile.md
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. 2d ago First seen · 49 lines · 18 tokens per session scan A 3a0788bdcb40

Subscribe to this mod's changes

performance-profiler is an agent published in the GitHub repository fatihkan/badi (7 stars, last pushed 15d ago), licensed MIT. It adds 18 tokens to every session and 348 once invoked, about $0.0001 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.

Related

Other agents, from other repositories