hot-paths

A guide to keeping an AI coding assistant fast during startup, before each conversation turn, and during each tool call. It covers delaying expensive work, reusing unchanged results, parallel startup tasks, and measuring load times.

In plain words
What is it for?
Use it when improving startup time, context preparation, schema validation, permission checks, or repeated Git and file-system lookups.
Why use it?
It reduces delays caused by loading large schemas, repeating expensive checks, or waiting for independent tasks one after another.

Skill for Claude CodeCodex

Part of the claude-code-superpowers plugin — 16 skills shipped together

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/techymt/claude-code-superpowers/hot-paths
Any agent
npx skills add TechyMT/claude-code-superpowers --skill hot-paths
Clone the repo
git clone --depth 1 https://github.com/TechyMT/claude-code-superpowers

Made for: Claude Code, Codex.

Or install claude-code-superpowers, the plugin that ships this one along with the rest of its 16 skills.

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,692 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 $0.00089 $0.01692
Opus 5 $0.00044 $0.00846
Sonnet 5 $0.00018 $0.00338
Haiku 4.5 $0.00009 $0.00169

Measured 2d ago against content hash 7d4d55d94896, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hot-paths 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.

skills/hot-paths/SKILL.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.

Hot Paths

The pattern

Claude Code has three hot paths: startup (module loading before first prompt), per-turn (context assembly before each API call), and per-tool-call (schema validation and permission checking for every tool use). Each has different performance constraints and different techniques.

For startup: use lazySchema() to defer Zod parsing, use feature() flags to eliminate dead code at build time, parallelize independent I/O with Promise.all(), and track timing with profileCheckpoint().

For per-turn: memoize expensive computations (git status, file system state) that don't change mid-conversation. Clear memoized values only when the underlying state actually changes.

For per-tool-call: lazySchema() ensures schema objects are built at most once per process lifetime (on first access), not once per call.

Why this matters

Claude Code starts a new process on every invocation. Users expect the prompt to appear in under a second. With ~512K lines of TypeScript across 1,884 files, naive module loading would be too slow. The techniques below are how the team keeps startup under a second on typical developer machines.

The per-turn hot path is also user-visible: every time the LLM needs to generate a response, Claude Code assembles a system prompt that includes git status, open file list, working directory, and recent file changes. This assembly runs before each API call. If it were slow, every turn would feel sluggish.

How to apply it

Startup:

  1. Wrap Zod schemas in lazySchema(() => z.object({...})) from utils/lazySchema.ts. The schema is built only when first accessed, not when the module loads.
  2. Use feature('FLAG_NAME') from bun:bundle for conditional imports. Bun evaluates these at build time and tree-shakes unused code. An unused feature flag means the code is not included in the bundle.
  3. Use profileCheckpoint('label') to measure time between initialization steps during development.
  4. For independent async initialization (config reads, keychain prefetch, MCP connection), use Promise.all().

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. 2d ago First seen · 160 lines · 89 tokens per session scan A 7d4d55d94896

Subscribe to this mod's changes

hot-paths is a skill published in the GitHub repository TechyMT/claude-code-superpowers (5 stars, last pushed 5mo ago), licensed MIT. It adds 89 tokens to every session and 1,692 once invoked, about $0.0004 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens