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.
npx agentmods add skills/vercel-labs/dev3000/analyze-bundlenpx skills add vercel-labs/dev3000 --skill analyze-bundlegit clone --depth 1 https://github.com/vercel-labs/dev3000What 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 | $0.00017 | $0.00699 |
| Opus 5 | $0.00009 | $0.00349 |
| Sonnet 5 | $0.00003 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
analyze-bundle 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 2d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
analyze-to-ndjson
Converts Next.js bundle analyzer binary .data files into grep/jq-friendly NDJSON.
Analyze artifacts
This workflow pre-generates analyzer artifacts in:
.next/diagnostics/analyze/ndjson/routes.ndjson.next/diagnostics/analyze/ndjson/sources.ndjson.next/diagnostics/analyze/ndjson/output_files.ndjson.next/diagnostics/analyze/ndjson/module_edges.ndjson.next/diagnostics/analyze/ndjson/modules.ndjson
Focus on reading these files and using their evidence to prioritize changes.
Output files
| File | What's in it |
|---|---|
modules.ndjson |
Global module registry (id, ident, path) |
module_edges.ndjson |
Module dependency graph (from, to, kind: sync/async) |
sources.ndjson |
Per-route source tree with sizes and environment flags |
chunk_parts.ndjson |
Granular size data: one line per (source, output_file) pair |
output_files.ndjson |
Per-route output files with aggregated sizes |
routes.ndjson |
Route-level summaries |
Browsing the output
Route overview
jq -s 'sort_by(-.total_compressed_size)' .next/diagnostics/analyze/ndjson/routes.ndjson
Find large sources
jq -s '
group_by(.full_path)
| map(max_by(.compressed_size))
| sort_by(-.compressed_size)
| .[0:10]
| .[] | {full_path, compressed_size, size, route}
' .next/diagnostics/analyze/ndjson/sources.ndjson
Client-side JS
grep '"client":true' .next/diagnostics/analyze/ndjson/sources.ndjson \
| grep '"js":true' \
| jq -s 'sort_by(-.compressed_size) | .[0:10] | .[] | {full_path, compressed_size}'
Module dependencies
grep '"from":42,' .next/diagnostics/analyze/ndjson/module_edges.ndjson | jq .to
grep '"to":42,' .next/diagnostics/analyze/ndjson/module_edges.ndjson | jq .from
grep 'react-dom' .next/diagnostics/analyze/ndjson/modules.ndjson | jq '{id, path}'
Output files for a route
grep '"route":"/"' .next/diagnostics/analyze/ndjson/output_files.ndjson \
| jq -s 'sort_by(-.total_compressed_size) | .[0:10] | .[] | {filename, total_compressed_size, num_parts}'
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.
- 2d ago First seen · 83 lines · 17 tokens per session scan A ec17b1a3dfe9
analyze-bundle is a skill published in the GitHub repository vercel-labs/dev3000 (1,573 stars, last pushed 6d ago), licensed MIT. It adds 17 tokens to every session and 699 once invoked, about $0.0001 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 skills, from other repositories
git-cleanup
Clean up local git branches and remotes accumulated from PR reviews. Use when the user asks to clean branches, remove stale remotes, or tidy up the local git state.
submit-pr-from-current-changes
Create a branch, commit existing local changes, push them, and open a pull request. Use when submitting current work as a PR.
bridge
Use when the user wants hyperflow's behavioral rules to apply outside the terminal CLI — in Claude Code Desktop, claude.ai web, or IDE extensions that don't load CLI plugins. Writes a managed doctrine block into the project's CLAUDE.md so autonomy + intent-routing + commit cadence + role separation + file-first rules…
memory
Use durable BB memory when prior project knowledge or cross-project user preferences can improve the current task, and save durable new learning through the bb memory CLI.
workflows
Execute a workflow script that orchestrates multiple subagents deterministically. Use when the user explicitly requests a workflow, multi-agent orchestration, parallel or sequential agent pipelines, structured agent outputs, or a durable background workflow run.
submit-a-plugin
Submit a bb plugin to the BB Community marketplace. Use whenever a user asks to submit, list, publish, or add a plugin to the BB marketplace, or asks for a marketplace pull request. This skill validates the plugin and release, creates the marketplace entry and icon, and opens the pull request.