analyze-function

A code-analysis command that examines one named function in a specified file, line by line.

In plain words
What is it for?
Use it to understand, review, debug, or improve a particular function. Run it with a filename and function name.
Why use it?
It turns unfamiliar function code into an explanation of its purpose, behavior, risks, and place in the wider codebase.

Command

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 commands/letitbk/claude-academic-setup/analyze-function
Clone the repo
git clone --depth 1 https://github.com/letitbk/claude-academic-setup
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,773 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 $0.00000 $0.01773
Opus 5 $0.00000 $0.00886
Sonnet 5 $0.00000 $0.00355
Haiku 4.5 $0.00000 $0.00177

Measured 2d ago against content hash 024a6abfd9fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-function 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.

commands/analyze-function.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze the specified function from the given file with detailed line-by-line breakdown.

Usage: /project:analyze-function filename:function_name or /project:analyze-function filename function_name

Arguments:

  • filename: The file containing the function to analyze
  • function_name: The name of the function to analyze

For the function $ARGUMENTS, I will:

  1. Read and locate the function in the specified file
  2. Provide context about the function's role in the system
  3. Analyze each line explaining:
    • What the code does technically
    • Why it's implemented this way
    • Performance implications
    • Edge cases and potential issues
    • Connection to the broader codebase
  4. Highlight critical details that might be missed from casual reading
  5. Explain design patterns and optimization techniques used
  6. Identify potential improvements or areas of concern

The analysis will focus on both the immediate functionality and the broader architectural context, helping you understand not just what the code does, but why it was written this way and what makes it effective (or potentially problematic) in its specific use case.

Example Analysis

Usage: /project:analyze-function train.py:detect_words_gpu

Context & Purpose

This function is part of the CurriculumManager class in a sophisticated GRPO (Group Relative Policy Optimization) training system. It's designed to efficiently detect and count words of different lengths in character-level sequences entirely on GPU to support curriculum learning stages that reward proper word formation.

Line-by-Line Analysis

Line 1326: Function Signature

def detect_words_gpu(self, sequences: torch.Tensor) -> torch.Tensor:
  • What: Defines a method taking character index sequences and returning word counts
  • Why: The _gpu suffix indicates this is optimized for GPU execution, crucial since this runs in the training loop where CPU-GPU transfers would be catastrophic for performance
  • Context: Part of curriculum learning where later stages reward proper word formation

Read the full file on GitHub · 146 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 · 146 lines · 0 tokens per session scan A 024a6abfd9fd

Subscribe to this mod's changes

analyze-function is a command published in the GitHub repository letitbk/claude-academic-setup (42 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,773 tokens. 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 2026-08-30.