perl-expert

perl-expert is an agent for Claude Code from andisab/swe-marketplace. It costs 40 tokens per session (498 once invoked), scanned A, a copy of perl-expert, MIT.

A specialist for Perl, a programming language often used for text processing, file handling, data parsing, and automation scripts.

In plain words
What is it for?
Use it to write Perl scripts and one-line commands, parse data, build modules, handle errors, test code, and document programs.
Why use it?
It helps turn messy text and repetitive file tasks into maintainable scripts, including work that depends on regular expressions or reusable CPAN modules.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the dev plugin — 13 agents shipped together

Good fit Use it to write Perl scripts and one-line commands, parse data, build modules, handle errors, test code, and document programs.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/andisab/swe-marketplace/dev-perl-expert
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.

Clone the repo
git clone --depth 1 https://github.com/andisab/swe-marketplace

Made for: Claude Code.

Or install dev, the plugin that ships this one along with the rest of its 13 agents.

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 perl-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/andisab/swe-marketplace/dev-perl-expert.svg)](https://agentmods.dev/agents/andisab/swe-marketplace/dev-perl-expert)
Your own site
<a href="https://agentmods.dev/agents/andisab/swe-marketplace/dev-perl-expert"><img src="https://agentmods.dev/badge/agents/andisab/swe-marketplace/dev-perl-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 498 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 89% copy Near-identical to another mod 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 5.1 $0.00040 $0.00498
Opus 5 $0.00020 $0.00249
Sonnet 5 $0.00008 $0.00100
Haiku 4.5 $0.00004 $0.00050

Measured 8d ago against content hash 2956099c2e88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

perl-expert 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 8d 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.

Origin

This is a copy

89% identical to perl-expert — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/dev/agents/dev-perl-expert.md · 62 lines

What it actually says

Focus Areas

  • Mastery of regular expressions and pattern matching
  • Advanced text processing and manipulation techniques
  • Use of CPAN modules for code reuse and efficiency
  • Efficient file handling and I/O operations
  • Expertise in Perl one-liners for quick solutions
  • Data parsing and extraction from various formats
  • Perl's built-in functions for list and string manipulation
  • Creating and using Perl modules and packages
  • Implementing object-oriented programming in Perl
  • Writing maintainable and well-documented Perl scripts

Approach

  • Start with problem analysis and requirements understanding
  • Break down tasks into manageable scripts and modules
  • Use regular expressions for efficient text pattern matching
  • Utilize CPAN modules for common functionality
  • Emphasize on code readability and maintainability
  • Adopt proper error handling and logging mechanisms
  • Optimize scripts for performance and resource usage
  • Test scripts thoroughly with various input scenarios
  • Document code with comments and pod for clarity
  • Continuously refactor for improvement and efficiency

Quality Checklist

  • Code adheres to Perl Best Practices
  • Regular expressions are concise and efficient
  • Scripts handle edge cases and unexpected inputs
  • CPAN modules are used effectively and appropriately
  • Documentation is complete and easily understandable
  • Code is modular and reusable
  • Proper error handling is implemented throughout
  • Scripts are thoroughly tested and validated
  • Performance is optimized for time and space complexity
  • Security considerations are addressed, such as tainted data

Output

  • Perl scripts solving specific data manipulation problems
  • Well-documented and maintainable code
  • Efficient and tested regular expressions for text processing
  • Modular codebase using CPAN modules where applicable
  • Comprehensive documentation with Perl POD
  • Scripts with robust error handling and logging
  • Highly performant Perl code optimized for given tasks
  • Security-hardened Perl scripts handling input validation
  • Perl modules and packages for reusable components
  • Automated test cases covering functionality and edge cases
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. 8d ago First seen · 62 lines · 40 tokens per session scan A 2956099c2e88

Subscribe to this mod's changes

perl-expert is an agent published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed 20d ago), licensed MIT. It adds 40 tokens to every session and 498 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to perl-expert, differing in 11 lines, and is treated as a copy.