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 agentmods add commands/nel-neru/libraium/format-syncgit clone --depth 1 https://github.com/nel-neru/LibrAIumWhat 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 | $0.00020 | $0.00793 |
| Opus 5 | $0.00010 | $0.00396 |
| Sonnet 5 | $0.00004 | $0.00159 |
| Haiku 4.5 | $0.00002 | $0.00079 |
Grade A, and why
format-sync 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 yesterday.
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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The LibrAIum data format is deliberately dual-implemented: the Rust core (desktop app) and the Node MCP server each parse, validate, and serialize the same files. After ANY change to the entry format, slugify, URL normalization, duplicate detection, or category master shape, run this synchronization procedure.
1. Identify what changed and mirror it
Walk this mapping and make the counterpart change on the other side:
| Concern | Rust | Node |
|---|---|---|
Frontmatter schema, field defaults (status: active, source: manual, stars: 0, optional-field omission) |
src-tauri/src/models.rs (EntryMeta) |
mcp-server/lib/store.js (parseEntry consumers, summarize defaults) |
Frontmatter split/parse/serialize (BOM handling, --- fences, body trimming, trailing newline) |
src-tauri/src/frontmatter.rs |
mcp-server/lib/store.js (splitFrontmatter, parseEntry, serializeEntry) |
slugify (allowed charset [a-z0-9-_.], / → -, lowercase, trim -) |
src-tauri/src/store.rs (slugify) |
mcp-server/lib/store.js (slugify) |
GitHub URL normalization (http/https/bare/git@ forms, .git, trailing /, /tree/...) |
src-tauri/src/store.rs (normalize_github_url) |
mcp-server/lib/store.js (normalizeGithubUrl) |
Duplicate detection (case-insensitive full_name) and entry id (<category>/<slug>) |
src-tauri/src/store.rs (find_duplicate, list_entries) |
mcp-server/lib/store.js (findDuplicate, listEntries, saveNewEntry) |
Both sides must accept, reject, and produce identical results. Where the change touches parsing, check the reject cases too (missing opening ---, unterminated frontmatter) — error behavior must match even if error text differs.
2. Add a fixture for the new shape
Add a fixture covering the new format shape to tests/fixtures/format/. Follow the naming pattern already used there (valid inputs that must round-trip, and invalid inputs both sides must reject). The conformance runner picks fixtures up automatically. Also extend the unit tests nearest the change (frontmatter::tests / store::tests in Rust) if the fixture alone can't express it.
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.
- yesterday First seen · 43 lines · 20 tokens per session scan A 87a08a634cad
format-sync is a command published in the GitHub repository nel-neru/LibrAIum (0 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 793 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.
Other commands, from other repositories
test-rust
Run Rust tests for Solana programs and backend services.
cargo-test
Command "cargo-test" from olorehq/olore, covering cargo-test(1), name, synopsis, description and documentation tests.
check
Run the local lint + test triad before committing.
good-question
Adaptive requirement elicitation - systematically reduce uncertainty through information-maximizing questions.
patterns
Manage learned patterns: save as skills/agents, analyze, review quality, and view statistics.
learn
Learn from your work: add notes, view patterns, and build knowledge.