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.
git clone --depth 1 https://github.com/nel-neru/LibrAIumnpx agentmods add skills/nel-neru/libraium/entry-authoringWrote 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/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.
<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="Reviewed on agentmods" width="80" 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 5.5 | $0.00014 | $0.01466 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 28d ago), licensed MIT. It adds 36 tokens to every session and 3,665 once invoked, about $0.0001 per session on Opus 5.5. 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.
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.
enzyme-sqlite-source
Connect an unfamiliar SQLite database to Enzyme without changing the source data. Inspect the database, decide which query columns represent identity, people, time, content, and folders, show real examples for approval, save a workspace program in the Enzyme language, and verify init and refresh. Use for email…
enzyme
Use Enzyme in an already activated Obsidian, Markdown, or Hermes workspace for working-memory retrieval, source-grounded exploration, search by keyword and meaning, runtime note-writing, and refresh. If the workspace is not initialized, follow the first-time setup section before normal retrieval.
paparats-search
Use when answering a question about code in the user's indexed repositories — where something is implemented, how a flow works, who calls a function, or what a change would affect. Explains when to use Paparats semantic search and when a text search is the better tool.
alice-project-memory
Use Alice as the project-scoped memory and continuity layer. Load before build or review work, and whenever a decision or constraint is worth keeping.