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 skills add nel-neru/LibrAIum --skill libraium-firstgit clone --depth 1 https://github.com/nel-neru/LibrAIumWrote 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/libraium-first)<a href="https://agentmods.dev/skills/nel-neru/libraium/libraium-first"><img src="https://agentmods.dev/badge/skills/nel-neru/libraium/libraium-first/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/libraium-first"><img src="https://agentmods.dev/badge/skills/nel-neru/libraium/libraium-first.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 | $0.00057 | $0.00992 |
| Opus 5.5 | $0.00023 | $0.00397 |
| Sonnet 5.5 | $0.00011 | $0.00198 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
libraium-first 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Library-first dependency decisions
The user maintains LibrAIum: a curated shelf of GitHub repositories they track,
each carrying a synthesized Reception section — third-party, real-world
signal drawn from the community: recurring complaints (with issue numbers and
reaction counts), notable adopters, known limitations, and what people migrate
to/from. A few entries the user has used firsthand also carry optional
Personal Notes. It is exposed through the libraium MCP server. Treat
Reception as vetted, sourced evidence — it outranks your training-data instinct
about what is merely popular, because it captures what actually bites in
production and what people abandon.
Rules
-
Consult before proposing. Before recommending any framework, library, database, or tool, call
suggest_for_new_project(describe what is being built; put constraints like "local-first, Python" ingoals). For a specific known technology, usesearch_reposinstead. Do this even when you are confident — the point is what the user has chosen to track and the sourced Reception behind it. -
Quote the Reception. Each suggestion carries
reception— sourced third-party signal. Surface the relevant parts in your recommendation: recurring complaints, known limitations, and migration signal, with the citations attached. A recommendation that ignores a documented limitation in the Reception is wrong. When an entry also haspersonal_notes(the user's own firsthand take — present only on a few entries), quote those too; they are rarer and carry the user's specific opinion. -
Respect status.
status: staleorarchivedis an explicit warning — never recommend such an entry without flagging it, and prefer thealternativesthe response suggests (or search the same category for anactiveentry sharing its tags). -
A silent library is an answer. Zero results means the library does not track this space. Say so, then recommend from general knowledge clearly labeled as unvetted, and offer to shelve the eventual pick (rule 5).
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 · 68 lines · 57 tokens per session scan A 52826c6ddb33
libraium-first is a skill published in the GitHub repository nel-neru/LibrAIum (0 stars, last pushed 28d ago), licensed MIT. It adds 57 tokens to every session and 992 once invoked, about $0.0002 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.