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 agentmods add skills/justanesta/claude-code-resources/python-performancenpx skills add justanesta/claude-code-resources --skill python-performancegit clone --depth 1 https://github.com/justanesta/claude-code-resourcesWhat 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 | $0.00057 | $0.00848 |
| Opus 5 | $0.00028 | $0.00424 |
| Sonnet 5 | $0.00011 | $0.00170 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
python-performance 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 yesterday.
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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Performance
Performance profiling, benchmarking, and optimization for Python.
Core Principle
Profile before optimizing - Use profiling tools to identify real bottlenecks. Premature optimization wastes time.
Profiling Tools Decision Matrix
| Tool | Use When | What It Shows |
|---|---|---|
| cProfile | Find slow functions | Function call times |
| line_profiler | Bottleneck in specific function | Time per line |
| memory_profiler | Memory issues suspected | Memory per line |
| py-spy | Production profiling | Sampling profiler |
| timeit | Micro-benchmarks | Execution time only |
Basic Profiling
cProfile - Function-level
import cProfile
import pstats
profiler = cProfile.Profile()
profiler.enable()
result = expensive_function()
profiler.disable()
stats = pstats.Stats(profiler)
stats.sort_stats('cumulative')
stats.print_stats(20)
line_profiler - Line-level
@profile
def slow_function():
results = []
for i in range(10000):
results.append(i ** 2)
return results
# Run: kernprof -l -v script.py
See profiling-workflow.md for:
- Complete profiling workflow
- Interpreting profiler output
Optimization Strategies
Algorithm Optimization (Biggest Impact)
# BAD - O(n²)
def find_duplicates_slow(items):
for i, item in enumerate(items):
for j, other in enumerate(items[i+1:]):
if item == other:
return True
# GOOD - O(n)
def find_duplicates_fast(items):
return len(items) != len(set(items))
Data Structure Choice
# Use set for membership testing
allowed_set = {1, 2, 3, 4, 5} # O(1) lookup
if x in allowed_set:
pass
See optimization-strategies.md for:
- Function call overhead
- String operations
- Dictionary optimizations
NumPy for Numerical Computing
import numpy as np
# BAD - Pure Python loop
result = [x**2 + 2*x + 1 for x in data]
# GOOD - NumPy vectorization (10-100x faster)
arr = np.array(data)
result = arr**2 + 2*arr + 1
What ships with it
6 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.
- yesterday First seen · 151 lines · 57 tokens per session scan A bcdf2496e3f0
python-performance is a skill published in the GitHub repository justanesta/claude-code-resources (2 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 848 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
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…