Scan entire codebases for over-engineering and generate a ranked remediation list.
npx skills add https://github.com/bketelsen/ytsejam --skill ponytail-audit
Please help me install this Agent Skill. Skill: ponytail-audit Source: https://github.com/bketelsen/ytsejam/tree/main/contrib/skills/ponytail-audit Command: npx skills add https://github.com/bketelsen/ytsejam --skill ponytail-audit
Whole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff — a ranked list of what to delete, simplify, or replace with stdlib/native/dep equivalents. Use when the user says "audit this codebase", "audit for over-engineering", "what can I delete from this repo", "find bloat in this repo", "ponytail-audit", or "/ponytail-audit". One-shot report — does not apply fixes.
Run ponytail-audit in the repository to dispatch a read-only scan and generate a ranked list of over-engineering findings.
High-intent search queries and answers about installing and using this skill.
To audit a codebase for over-engineering, you can run a whole-repo scan that analyzes the entire file tree to identify bloated patterns and generate a ranked remediation list. The audit operates conservatively and read-only, outputting a findings table without applying fixes.
Finding code to delete across a large repository involves scanning the entire tree for categories like stdlib reinventions, unnecessary dependencies, and YAGNI violations. The scan produces a ranked list of what to delete, simplify, or replace with native equivalents.
Yes, you can focus static analysis on specific categories like vendor code, dependencies, or stdlib reinventions. The scan allows you to configure excludes and confirm the root directory and focus area before dispatching the read-only audit.
No, a codebase audit for bloat does not modify your source files. It implements a conservative, read-only workflow that generates a report containing a ranked findings table and a NOT BLOAT section for design review.
When scanning a repo for over-engineering, the categories to hunt include code to delete, stdlib replacements, native equivalents, dependency substitutions, YAGNI violations, and areas to shrink. A conservative stance ensures intentional design choices are separated into a NOT BLOAT section.
jhlee0409Scan codebases for OWASP Top 10 vulnerabilities with read-only analysis.
shouqitaoScan code for disallowed technologies and over-engineered patterns.
jikig-aiScan git-diff-selected source files with semgrep for vulnerability patterns.
malinskibeniaminAudit a repository for over-engineering and bloated code.
