Ponytail Audit
Audit a whole repo for over-engineering and get a ranked cut-list
- What
- Audit a whole repo for over-engineering and get a ranked cut-list
- Cost
- Free
- Needs
- none beyond a working agent; read access to the repository you want reviewed
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — a repo-wide audit skill that scans the whole tree (not just a diff) for over-engineering and returns a ranked list of what to delete, simplify, or replace, biggest cut first. Findings are tagged: `delete` (dead code, speculative features), `stdlib` (hand-rolled things the standard library ships — names the function), `native` (platform already does it — names the feature), `yagni` (single-implementation abstractions, config nobody sets), `shrink` (same logic, fewer lines). Output is one line per finding ending with a net line-count and dependency estimate (`Lean already. Ship.` when there's nothing to cut). It references the sibling `ponytail-review` from the same repo, but defines its own tags and workflow, so it works standalone. By @dietrichgebert, listed here with credit to its creator. Honest caveats: read-only — it lists findings and applies nothing; correctness bugs, security holes and performance are explicitly out of scope, so pair it with a normal review pass; and the audit's taste is opinionated — "over-engineered" is a judgment call, not a measurement. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Ponytail Audit is a free Muse skill that audits a repository for over-engineering, scanning the tree not just a diff, and returns a ranked cut-list biggest cut first. Findings tagged delete for dead code, speculative features, stdlib for hand-coded standard-library things, native for platform features, yagni for single-implementation abstractions, and shrink for the same logic in fewer lines.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 9cc65d0Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: none beyond a working agent; read access to the repository you want reviewed Install "Ponytail Audit" for me. Audit a whole repo like a senior developer who just inherited it: bugs, security holes, load behavior, risky untested code, slow paths and bloat — ranked, each finding explained in plain English. Note: since our last review (2026-10-08) the repo was restructured from an over-engineering-focused scan into this full senior-developer audit with a new 4-step workflow. Repository: https://raw.githubusercontent.com/dietrichgebert/ponytail/9cc65d03aa2da1db7121b912d03596409ee340b8/skills/ponytail-audit/SKILL.md Pinned version: install the code at commit 9cc65d03aa2da1db7121b912d03596409ee340b8 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file for the dietrichgebert-ponytail-audit skill from the repository into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "dietrichgebert-ponytail-audit". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. any accounts, API keys, or CLI tools mentioned in the prerequisites above). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. Never ask me to paste secrets in chat — credentials go through the secure vault or environment variables. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 9cc65d0 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.