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.
git clone --depth 1 https://github.com/andisab/swe-marketplaceWrote 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.
[](https://agentmods.dev/agents/andisab/swe-marketplace/dev-perl-expert)<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>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.
| Model | Per session | Once 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 |
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.
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.
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
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.
- 8d ago First seen · 62 lines · 40 tokens per session scan A 2956099c2e88
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.
Other agents, from other repositories
csharp-reviewer
C#-specific code reviewer. Audits for .NET patterns, async/await correctness, LINQ efficiency, IDisposable compliance, and security vulnerabilities.
java-reviewer
Java-specific code reviewer. Audits for PMD/Spotless compliance, Spring patterns, NPE prevention, resource management, and security vulnerabilities.
kotlin-reviewer
Kotlin-specific code reviewer. Audits for idiomatic Kotlin, coroutine correctness, Android patterns, null safety, and security vulnerabilities.
rust-reviewer
Rust-specific code reviewer. Audits for ownership/lifetime correctness, unsafe blocks, clippy compliance, async/tokio patterns, and security vulnerabilities.
go-reviewer
Go-specific code reviewer. Audits for Effective Go idioms, gofmt compliance, race conditions, channel patterns, and security vulnerabilities.
typescript-reviewer
TypeScript-specific code reviewer. Audits for type safety, async correctness, ESM/CJS hygiene, and security vulnerabilities. Returns severity-rated findings — e.g.,…