Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/nel-neru/libraium/entry-authoring)<a href="https://agentmods.dev/skills/nel-neru/libraium/entry-authoring"><img src="https://agentmods.dev/badge/skills/nel-neru/libraium/entry-authoring.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 | $0.00036 | $0.03665 |
| Opus 5 | $0.00018 | $0.01833 |
| Sonnet 5 | $0.00007 | $0.00733 |
| Haiku 4.5 | $0.00004 | $0.00366 |
Grade A, and why
entry-authoring 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 5d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LibrAIum entry authoring — house style
One repo = one file at data/entries/<category-id>/<slug>.md, where slug = slugify(full_name): lowercase, / and any character outside [a-z0-9-_.] become -, leading/trailing - trimmed. Owner/Repo.js → owner-repo.js. The file is YAML frontmatter + Markdown body. The seven seeded entries in data/entries/ are the reference corpus — when in doubt, imitate them.
Frontmatter
Fields are exactly EntryMeta (src-tauri/src/models.rs). Never invent keys — the Rust parser and the MCP server both consume this schema. Keep the field order below (it matches the existing entries and the Rust struct):
| Field | Required | Semantics |
|---|---|---|
github_url |
yes | Canonical form only: https://github.com/<owner>/<repo> — no .git, no trailing /, no /tree/... |
full_name |
yes | owner/repo exactly as GitHub reports it (case preserved). Duplicate detection compares this case-insensitively |
category |
yes | A category id from data/master/categories.yaml (kebab-case). Must match the directory the file lives in |
tags |
default [] |
Flow style: tags: [vector-db, rag, rust] — see tag conventions below |
stars |
default 0 |
Integer from the GitHub API (stargazers_count) at last check — never guessed, never "21.4k" |
language |
optional | GitHub's primary language with GitHub's capitalization (Rust, Python, TypeScript). Omit the key if unknown |
last_github_push |
optional | YYYY-MM-DD date part of the API's pushed_at. Omit if unknown |
last_checked |
optional | YYYY-MM-DD when metadata was last refreshed from the API. Set to today when you fetch real data |
status |
default active |
Enum: active | stale | archived. Auto-managed by refresh (push older than the stale threshold ⇒ stale; GitHub archived ⇒ archived) — don't hand-set stale without reason |
source |
default manual |
Enum: manual | mcp | x-collection. Hand-authored entries are manual; the MCP add_repo tool writes mcp |
added_date |
optional | YYYY-MM-DD the entry joined the library. Set once, never touched again |
reception_gathered |
optional | YYYY-MM-DD the ## Reception section was last synthesized. Stamped by /reception; drives freshness (an entry is reception_stale after 180 days) |
superseded_by |
optional | Flow list of owner/repo full_names this entry has been superseded by, e.g. superseded_by: [langchain-ai/langgraph]. Store it on the stale/old entry, pointing FORWARD; the inverse (supersedes) is derived at read time, never stored. A target need not be shelved yet. Omit entirely when empty (never []) |
pairs_with |
optional | Flow list of owner/repo full_names this entry pairs well with (symmetric affinity). Store on ONE side only — it is unioned at read time with entries that point back. Omit entirely when empty |
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.
- 5d ago First seen · 180 lines · 36 tokens per session scan A f63aa2aefb84
entry-authoring is a skill published in the GitHub repository nel-neru/LibrAIum (0 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 3,665 once invoked, about $0.0002 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.
Other skills, from other repositories
vault
Search, read, write, and manage files in the Kept conversation vault. Use when the user asks about past conversations, wants to save notes, needs to find specific content, or wants to organize their vault.
seller-research
Use when researching a merchant, storefront, marketplace seller, or merchant of record for a buying decision, especially when identity, refund terms, fulfillment, counterfeit risk, domain history, or independent buyer outcomes are uncertain.
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
vault-for-llm
Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.
anyr
Use when reading, searching, creating, or updating Anytype documents (objects, spaces, types, properties, files, chats) from the command line with the configured anyr CLI, including JSON output patterns for scripting.
memem-welcome
Re-show the full memem welcome screen regardless of whether the user has seen it before. Use when the user wants to see the intro, tutorial, or welcome again.