Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kensaurus/cursor-kenjinpx agentmods add skills/kensaurus/cursor-kenji/audit-bundle-sizeWrote 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/skills/kensaurus/cursor-kenji/audit-bundle-size)<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/audit-bundle-size"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/audit-bundle-size/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kensaurus/cursor-kenji/audit-bundle-size"><img src="https://agentmods.dev/badge/skills/kensaurus/cursor-kenji/audit-bundle-size.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 106 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 270 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00065 | $0.02691 |
| Opus 5.5 | $0.00026 | $0.01076 |
| Sonnet 5.5 | $0.00013 | $0.00538 |
| Haiku 4.5 | $0.00006 | $0.00269 |
Grade A, and why
audit-bundle-size 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
audit-bundle-size — Find and Eliminate Bundle Bloat
Degree of freedom: MIXED — Offender triage and swap choice [HIGH freedom];
Phase 1 production build + analyser [LOW freedom — run exactly].
Audit-and-fix exception. Measure the payload, then shrink it. Runtime slowness →
audit-performance.Fix only what the measurement named, in the files it named; a repo-wide dependency sweep the report did not list is a different session. Edit surgically — the offending import,
dynamic()boundary, or chunk config — rather than rewriting whole files. Pre-existing bugs met on the way go in the report as follow-ups. Add or change tests only where the repo already keeps them for that surface; scratch checks and generated analyser reports (client.html,bundle-report.html) stay out of the commit. AnANALYZE=true-guarded analyser config stays only if the repo already keeps one.
Every kilobyte of JavaScript the browser must download, parse, and compile before showing anything costs real users real time. A large initial bundle is the #1 avoidable cause of slow LCP and poor Core Web Vitals. Find exactly what is bloating it and fix each item.
How to reason — Observe → Interpret → Classify → Severity
- Observe — quote First Load JS / chunk gzip and the treemap contributor (
file+ package) - Interpret — is this unused code on the critical path, a duplicate, or a missing split?
- Classify — giant-vendor / full-library import / missing-lazy / unused-dep / dev-in-prod / duplicate
- Severity — by gzip on the initial route: >250 KB First Load JS = review; do not delete a feature to save KB
Worked example
Observe: Next.js First Load JS 420 KB gzip. Treemap: default
lodashimport inlib/utils.ts;momentwith all locales in the shared layout. Interpret: two libraries pull unused code onto every route. Classify: full-library import + oversized date lib. Severity: High — over the 250 KB review threshold. Finding: namedlodash/debounce+ replacemomentwithdayjs; remesure First Load JS before claiming a save.
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.
- 1mo ago Changed · +10 lines · -17 tokens per session 6a298a426b9c
- 1mo ago First seen · 287 lines · 82 tokens per session scan A 30d2f03516fb
audit-bundle-size is a skill published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 26d ago), licensed MIT. It adds 65 tokens to every session and 2,691 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
data-export
A backend service for exporting data in Excel, CSV, or JSON while tracking each export as a background task.
noteplan
Read, search, create, and edit NotePlan notes and daily logs directly via the filesystem. Use this skill whenever the user references NotePlan, daily notes, weekly notes, project notes, or wants to check/update their planning. Triggers: 'noteplan', 'daily note', 'today's note', 'weekly note', 'check my notes', 'add to…
google-sheets
Safe workflow for reading, mapping, and writing Google Sheets without shifting columns or overwriting the wrong ranges. Use when the user wants to read, update, or append spreadsheet data, fix sheet structure, or sync data into Google Sheets.
xlsx-toolkit
Audit Microsoft Excel (.xlsx) workbooks for formula density, external references, named ranges, hidden sheets, and data validation. Use when reviewing a financial model, sharing a workbook externally, or checking for data leakage.
markitdown
A local document-conversion guide built around MarkItDown, a tool that turns files such as DOCX, PDF, PPTX, XLSX, images, HTML, and CSV into Markdown text.
prismer-google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.