bulk-add

bulk-add is a command for Claude Code from nel-neru/LibrAIum. It costs 25 tokens per session (577 once invoked), scanned A, original, MIT.

A command for adding several GitHub repositories to a curated library at once, either from a list of URLs or from GitHub stars. It creates draft entry files, skips duplicates, and validates the results.

In plain words
What is it for?
Use it to batch-add approved repository URLs or generate a reviewable list from starred repositories filtered by age, language, or star count.
Why use it?
It removes repetitive repository intake work and can turn a large star list into candidates for review before anything is added.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/nel-neru/libraium/bulk-add
Clone the repo
git clone --depth 1 https://github.com/nel-neru/LibrAIum

Made for: Claude Code.

Wrote 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.

agentmods badge for bulk-add

README.md
[![agentmods](https://agentmods.dev/badge/commands/nel-neru/libraium/bulk-add.svg)](https://agentmods.dev/commands/nel-neru/libraium/bulk-add)
Your own site
<a href="https://agentmods.dev/commands/nel-neru/libraium/bulk-add"><img src="https://agentmods.dev/badge/commands/nel-neru/libraium/bulk-add.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 577 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00025 $0.00577
Opus 5 $0.00013 $0.00289
Sonnet 5 $0.00005 $0.00115
Haiku 4.5 $0.00003 $0.00058

Measured 2d ago against content hash 0fc2ec6c84ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bulk-add 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.

.claude/commands/bulk-add.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Batch intake into the library for: $ARGUMENTS

Network runs only inside this explicitly-invoked command. Export a token first so 10+ calls don't hit the anonymous 60/hr limit:

export GITHUB_TOKEN=$(gh auth token)

Path A — a list of URLs

  1. If the user gave URLs (optionally url,category per line, or a shared --category), run the intake:

    node scripts/bulk-add.mjs <url>... --category <id>
    # or:  node scripts/bulk-add.mjs --file targets.txt
    

    The script normalizes → dedupes → fetches metadata → writes a skeleton entry per new repo (placeholder - note), skipping duplicates and continuing past failures, then runs validate-data. Read back its added/skipped/failed summary to the user.

Path B — harvest from GitHub stars

  1. Produce a triage table (writes nothing):

    node scripts/bulk-add.mjs --from-stars --min-stars 500 --pushed-within 365
    # --user <name> for someone else's public stars; --language <L> to narrow
    

    Each row is a ready url,category line with a lexically-proposed category. Review it with the user — fix UNMATCHED or wrong categories — then feed the approved lines into Path A (--file or --stdin).

Draft real notes (both paths)

The skeletons carry a placeholder note that /curate-review would flag. For each new entry, follow the entry-authoring skill:

  • Read the repo's README (WebFetch) and write a ≤2-sentence summary replacing the raw GitHub description.
  • Add 2–5 attributive ## Reception bullets — third-party signal (complaints, adopters, limitations, migration, maturity), every claim sourced; never fabricated firsthand experience. Cross-link related library entries. See the entry-authoring skill's "Reception voice".
  • Add 3–6 kebab-case tags, reusing the existing vocabulary (node scripts/curation-report.mjs shows it) before minting new ones.
  • Optionally add a ## Setup section with verified install commands.

Then node scripts/validate-data.mjs --data-dir data, show git diff, and let the user review. Do not commit — they do.

Read the full file on GitHub · 46 lines

Changes

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.

  1. 2d ago First seen · 46 lines · 25 tokens per session scan A 0fc2ec6c84ba

Subscribe to this mod's changes

bulk-add is a command published in the GitHub repository nel-neru/LibrAIum (0 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 577 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 2026-08-31.