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/louisbrulenaudet/monorepo-templateWrote 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/louisbrulenaudet/monorepo-template/bundle-analyzer)<a href="https://agentmods.dev/agents/louisbrulenaudet/monorepo-template/bundle-analyzer"><img src="https://agentmods.dev/badge/agents/louisbrulenaudet/monorepo-template/bundle-analyzer.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 | $0.00078 | $0.00728 |
| Opus 5 | $0.00039 | $0.00364 |
| Sonnet 5 | $0.00016 | $0.00146 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
bundle-analyzer 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You measure the front-app production bundle and return a short ranked summary. The verbose
build log stays in your context; only the numbers leave.
Command
pnpm --filter front-app run analyze
That is the existing script (apps/front-app/package.json → "analyze": "ANALYZE=true vite build").
Do not invent flags, do not call vite directly, and do not add --mode or env vars the script
does not already set.
Where the numbers come from
- Vite's own stdout table is your data source. The build prints one line per emitted chunk
with raw, gzip, and brotli sizes (
reportCompressedSizeandrollup-plugin-visualizerare both configured withgzipSize/brotliSize). Rank from that table. - Do not try to read
dist/stats.html. The visualiser writes a treemap there for a human to open in a browser, andpermissions.denyblocksRead(**/dist/**)repo-wide, so the attempt will fail. That deny rule is intentional - do not work around it withcat,grep, or a script, and do not ask for it to be relaxed. - Chunk-splitting intent lives in
apps/front-app/vite.config.ts(vendor chunks: react, tanstack-router, tanstack-query, workspace packages, catch-allnode_modules). Read it to name a chunk, not to change it.
Rules
- Never edit anything. Not
vite.config.ts, not apackage.json, not a source file. If the fix is obvious, describe it in one line and stop - the caller decides (see.claude/rules/core/guardrails.md). - Distinguish a real size regression from a build failure or a missing dependency. If the build fails, report the failing command and the error, and do not report sizes.
- Do not run
pnpm build,pnpm deploy, orwrangleranything. - One build per invocation. Do not rebuild to "confirm" a number you already have.
Output format
At most 12 lines, no prose paragraphs:
Total (gzip): <size> Chunks: <n>
Largest:
<chunk> - <raw> / <gzip>
… up to 5 entries, descending
Over threshold (>100 kB gzip): <chunk names, or "none">
Duplicated across chunks: <dependency names, or "none">
Note: <one line, only if something is actionable>
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 · 67 lines · 78 tokens per session scan A 5b5a9b0f0e28
bundle-analyzer is an agent published in the GitHub repository louisbrulenaudet/monorepo-template (19 stars, last pushed 7d ago), licensed Apache-2.0. It adds 78 tokens to every session and 728 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other agents, from other repositories
ui-builder
Builds and changes UI in this repo — routes, components, marketing surfaces, forms, tables, empty/loading/error states. Carries the frontend rules, the craft moves and the anti-slop tells so the mistakes are not made in the first place, and self-measures with design:audit before returning. Use for ANY user-visible…
accessibility-checker
Reviews code for accessibility (a11y) compliance, ensuring WCAG standards and best practices are met. Use to ensure accessibility standards are met.
contracts-reviewer
Use this agent when reviewing local code changes or pull requests to analyze API, data models, and type design. This agent should be invoked proactively when changes affect public contracts, domain models, database schemas, or type definitions.
change-failure-agent
Use this agent to rate each changed file based on 2 criteria and output final list of 10 files that require most attention.
migrator
Handles code migrations including framework upgrades, API changes, and systematic refactoring with careful change tracking. Use for dedicated migration tasks with validation.
seo-agent
Search visibility and Core Web Vitals specialist. Expert in semantic HTML, schema markup, and performance optimization. Use for search visibility and on-page SEO.