review-performance

review-performance is a skill for Claude Code, Codex from paultyng/skill-issue. It costs 74 tokens per session (2,010 once invoked), scanned A, original, MIT.

A review guide for finding code that uses too much processor time or memory, especially on frequently used paths. It also checks whether performance tests and benchmarks are sufficient.

In plain words
What is it for?
Use it for performance audits, profiling reviews, benchmark reviews, latency or throughput checks, allocation reviews, and investigations of whether code is fast enough.
Why use it?
It helps locate slow code and unnecessary memory use when performance is an explicit concern. It keeps performance checks focused instead of adding them to every ordinary code review.

Skill for Claude CodeCodex

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 skills/paultyng/skill-issue/review-performance
Any agent
npx skills add paultyng/skill-issue --skill review-performance
Clone the repo
git clone --depth 1 https://github.com/paultyng/skill-issue

Made for: Claude Code, Codex.

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 review-performance

README.md
[![agentmods](https://agentmods.dev/badge/skills/paultyng/skill-issue/review-performance.svg)](https://agentmods.dev/skills/paultyng/skill-issue/review-performance)
Your own site
<a href="https://agentmods.dev/skills/paultyng/skill-issue/review-performance"><img src="https://agentmods.dev/badge/skills/paultyng/skill-issue/review-performance.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,010 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 $0.00074 $0.02010
Opus 5 $0.00037 $0.01005
Sonnet 5 $0.00015 $0.00402
Haiku 4.5 $0.00007 $0.00201

Measured 5d ago against content hash 7b9cc5bf79e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-performance 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 5d 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- Findings must cite probed evidence (`path:line`, grep output, command result), not pattern-matched suspicion. Per `~/.claude/rules/probe-not-assume.md`.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/review-performance/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Review

Structured review of hot-path performance, allocation patterns, and benchmark coverage. Opt-in only — performance is rarely the bottleneck for new code, and a perf review on every PR is noise. Run when the user explicitly asks, or when a feature is performance-sensitive by nature (hot path, fanout, large-data).

Out of scope (defer to siblings):

  • Concurrency safety (race, deadlock, leak) → review-reliability
  • Cardinality / metric cost → review-observability
  • Database query plans / index design → review-database

review-performance looks at code-level allocation and CPU hotspots, benchmark sufficiency, and obvious algorithmic complexity issues.

Workflow

1. Scope and explore

  • Confirm scope with the user: full codebase, specific packages/directories, changed files only (PR or branch diff), or a specific hot path.
  • Resolve scope. Same conventions as siblings:
    • Changed files (PR or branch): git diff --name-only --diff-filter=d <base>...HEAD; filter to source files.
    • Explicit paths/packages: include all relevant source files.
    • Full codebase: walk source files.
  • If invoked from review-all (only when the user opted in): receive file_list, package_paths, has_changes, base_ref, REVIEW_DIR, and pr_url.

This skill is primarily Go-focused because the existing review-* corpus targets Go; it has cross-language sections in reference.md but the deepest checklist is for Go.

2. System overview

Produce a brief summary covering:

  • Languages and runtimes in scope
  • Identifiable hot paths (RPC handlers, queue consumers, batch jobs)
  • Existing benchmark coverage (Go: Benchmark* functions; presence of testing.B)
  • Observed SLOs / latency targets if documented in REVIEW.md, README.md, or runbooks

3. Launch investigation subagent

Launch a single investigation subagent (subagent_type="generalPurpose", model: sonnet per subagent-model-routing) with the system overview and in-scope file list.

Read the full file on GitHub · 166 lines

Files

What ships with it

1 file 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.

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. 5d ago First seen · 166 lines · 74 tokens per session scan A 7b9cc5bf79e3

Subscribe to this mod's changes

review-performance is a skill published in the GitHub repository paultyng/skill-issue (9 stars, last pushed 24d ago), licensed MIT. It adds 74 tokens to every session and 2,010 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.