codeflash

codeflash is a skill for Claude Code, Codex from Mahesh8214/ShadowShield-MCP. It costs 23 tokens per session (232 once invoked), scanned A, original, MIT.

A tool-assisted workflow for making Python code run faster while checking that its behaviour stays the same. It benchmarks code and uses pytest tests, including tests it can generate for regression checking.

In plain words
What is it for?
Optimizing a Python file or function, generating regression tests, running pytest, and reviewing before-and-after execution times.
Why use it?
It helps identify slow functions and compare an optimization with the original while catching unintended changes.

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/mahesh8214/shadowshield-mcp/codeflash
Any agent
npx skills add Mahesh8214/ShadowShield-MCP --skill codeflash
Clone the repo
git clone --depth 1 https://github.com/Mahesh8214/ShadowShield-MCP

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 codeflash

README.md
[![agentmods](https://agentmods.dev/badge/skills/mahesh8214/shadowshield-mcp/codeflash.svg)](https://agentmods.dev/skills/mahesh8214/shadowshield-mcp/codeflash)
Your own site
<a href="https://agentmods.dev/skills/mahesh8214/shadowshield-mcp/codeflash"><img src="https://agentmods.dev/badge/skills/mahesh8214/shadowshield-mcp/codeflash.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 232 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 $0.00023 $0.00232
Opus 5 $0.00012 $0.00116
Sonnet 5 $0.00005 $0.00046
Haiku 4.5 $0.00002 $0.00023

Measured 4d ago against content hash 15849d4ddb27, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codeflash 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 4d 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.

.agents/skills/codeflash/SKILL.md · 35 lines

What it actually says

Codeflash AI Skill

Codeflash automatically analyzes, benchmarks, tests, and optimizes Python code for maximum performance while maintaining behavior correctness through existing or generated pytest suites.

Installation & Environment Setup

Install Codeflash via pip:

pip install codeflash

Initialize configuration (if configuring API keys or repository settings):

codeflash init
  1. Identify Target Functions: Find slow or frequently executed functions (e.g., data processing, log parsing, model inference wrappers).
  2. Run Benchmarks & Optimization:
    codeflash --file <path_to_file.py>
    
    Or target a specific function:
    codeflash --file <path_to_file.py> --function <function_name>
    
  3. Verify Tests: Ensure generated regression tests pass cleanly using pytest.
  4. Review Performance Gains: Evaluate the benchmark output comparing execution time before and after optimization.
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. 4d ago First seen · 35 lines · 23 tokens per session scan A 15849d4ddb27

Subscribe to this mod's changes

codeflash is a skill published in the GitHub repository Mahesh8214/ShadowShield-MCP (0 stars, last pushed 15d ago), licensed MIT. It adds 23 tokens to every session and 232 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.