agentmods.dev

add-entry

add-entry is a command for Claude Code from nel-neru/LibrAIum. It costs 20 tokens per session (1,211 once invoked), scanned A, original, MIT.

A command for researching a GitHub repository and adding it as a curated entry to the LibrAIum library. GitHub is a site where developers publish and maintain code projects.

In plain words
What is it for?
Use it when adding a new GitHub project to the library, including checking its URL, metadata, duplicates, and entry details.
Why use it?
It removes the need to manually collect project details and helps prevent duplicate entries or notes that are not supported by the repository.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/validate-data.mjs --data-dir data.

not rated 0repo 1mo ago A scan 20 tokens original MIT

Good fit Use it when adding a new GitHub project to the library, including checking its URL, metadata, duplicates, and entry details.

Compare 6 commands from other repositories ↓
View source ↗ nel-neru/LibrAIum
Install

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.

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

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 add-entry

README.md
[![agentmods](https://agentmods.dev/badge/commands/nel-neru/libraium/add-entry/github.svg)](https://agentmods.dev/commands/nel-neru/libraium/add-entry)
Your own site
<a href="https://agentmods.dev/commands/nel-neru/libraium/add-entry"><img src="https://agentmods.dev/badge/commands/nel-neru/libraium/add-entry/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.

agentmods 80×15 button for add-entry

Your own site · 80×15
<a href="https://agentmods.dev/commands/nel-neru/libraium/add-entry"><img src="https://agentmods.dev/badge/commands/nel-neru/libraium/add-entry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,211 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00020 $0.01211
Opus 5.5 $0.00008 $0.00484
Sonnet 5.5 $0.00004 $0.00242
Haiku 4.5 $0.00002 $0.00121

Measured 2mo ago against content hash a1e26abe83ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

add-entry scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s https://api.github.com/repos/<owner>/<repo>
.claude/commands/add-entry.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add a new curated entry to the LibrAIum library for: $ARGUMENTS

Follow this workflow in order. If the entry-authoring skill is available, load it — it is the authoritative house style; the essentials are repeated below.

1. Normalize the URL and check for duplicates

  • Derive owner/repo from the input. Accepted URL shapes and normalization rules are implemented in mcp-server/lib/store.js (normalizeGithubUrl): strip protocol, trailing /, .git, and any /tree/... suffix. The canonical form stored in github_url is https://github.com/<owner>/<repo>.
  • Check for an existing entry (duplicate detection compares lowercased full_name, so search case-insensitively): 
    grep -ril "^full_name: owner/repo" data/entries/
    or reuse the real implementation: 
    node -e 'import("./mcp-server/lib/store.js").then(s => console.log(s.findDuplicate("data", "owner/repo")))'
  • If a duplicate exists, stop: show the user the existing entry and ask whether they want to update it instead.

2. Research the repo

  • Fetch real metadata from the GitHub API — prefer gh when available, otherwise plain HTTPS: 
    gh api repos/<owner>/<repo>        # or:
curl -s https://api.github.com/repos/<owner>/<repo>
    Take stargazers_count → stars, language → language, pushed_at (date part, YYYY-MM-DD) → last_github_push, and archived (true ⇒ status: archived).
  • The response's full_name is authoritative — a renamed repo 301-redirects and the API returns the NEW name. If it differs from what you derived in step 1: use it for full_name, rebuild github_url as https://github.com/<full_name>, and re-run the step-1 duplicate check under the new name (an entry may already be shelved there). This mirrors guard_redirected_duplicate in both code add paths.
  • WebFetch the repository's README (https://github.com/<owner>/<repo>) to understand what it actually does, how mature it is, and what it pairs with. Look for gotchas in the docs (limits, platform caveats, migration notes).
  • If the network is unavailable: ask the user for stars/language, or omit the optional fields — never invent numbers or dates.

Read the full file on GitHub · 61 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. 2mo ago First seen · 61 lines · 20 tokens per session scan A a1e26abe83ff

Subscribe to this mod's changes

add-entry is a command published in the GitHub repository nel-neru/LibrAIum (0 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 1,211 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeResearchawesome-listknowledge-managementlocal-firstmcpmcp-server
Related

add-entry compared with commands from other repositories

add-entry next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
add-entrynel-neru/LibrAIumCommand01mo agoMITA20Claude Code
iai-directiveCodeAbra/iai-personal-memory-engineCommand9206d agoMITB17Claude Code
blzoutfitter-dev/blzCommand282mo agoMITA10Claude Code
good-questionh315uk3/symbiosisCommand127mo agoAGPL-3.0A14Claude Code
learnh315uk3/symbiosisCommand127mo agoAGPL-3.0A14Claude Code
workflowsh315uk3/symbiosisCommand127mo agoAGPL-3.0A13Claude Code
activeh315uk3/symbiosisCommand127mo agoAGPL-3.0A10Claude Code