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/scoutgit 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 | $0.00030 | $0.00960 |
| Opus 5 | $0.00015 | $0.00480 |
| Sonnet 5 | $0.00006 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
scout 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 2d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scout candidates for: $ARGUMENTS
Explicitly user-invoked — the GitHub search below is the only network call. Export a token so searches don't hit the anonymous limit:
export GITHUB_TOKEN=$(gh auth token)
1. Frame the search
- Shelf mode (
$ARGUMENTSis a category id): read that shelf's existing entries and their tags —node scripts/curation-report.mjsshows shelf sizes and the tag vocabulary. Derive 2-3 single-topic queries from the category's name/description indata/master/categories.yamlplus its dominant tags (e.g.audio-voice→speech recognition,text to speech,audio processing). One topical phrase per query beats a long AND — the search narrows fast. - Succession mode (
--replace <entry-id>): read that stale/archived entry's tags and summary; seed the queries from its tags so the candidates are drop-in replacements.
2. Search with floors (verified recipe)
Run each query — adjust --stars to the shelf (flagship shelves want a higher floor; niche shelves lower):
gh search repos --sort stars --limit 15 --archived=false --stars '>2000' \
--json fullName,stargazersCount,pushedAt,license,description \
'<query>'
Use --sort updated instead when you care about liveness over popularity. Drop anything whose pushedAt is older than ~12-18 months (dormant), and awesome-lists / tutorial collections (not real tooling).
3. Dedupe against the library AND the rejected-candidates memory
Filter every hit through two checks — never propose something already shelved (findDuplicate, case-insensitive on full_name, catches it even under a different category), and never re-surface a repo already evaluated and consciously declined (findRejected, data/master/rejected.yaml):
gh search repos --sort stars --limit 15 --archived=false --stars '>2000' \
--json fullName,stargazersCount,pushedAt,license,description '<query>' \
| node --input-type=module -e '
import { findDuplicate } from "./mcp-server/lib/store.js";
import { findRejected } from "./mcp-server/lib/rejected.js";
let s=""; process.stdin.on("data",d=>s+=d).on("end",()=>{
for (const r of JSON.parse(s)) {
if (findDuplicate("data", r.fullName) || findRejected("data", r.fullName)) continue;
console.log(`${r.fullName}\t★${r.stargazersCount}\t${(r.pushedAt||"").slice(0,10)}\t${r.license?.key||"—"}\t${(r.description||"").slice(0,80)}`);
}
});'
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.
- 2d ago First seen · 66 lines · 30 tokens per session scan A d3c3882e8f32
scout is a command published in the GitHub repository nel-neru/LibrAIum (0 stars, last pushed 6d ago), licensed MIT. It adds 30 tokens to every session and 960 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 commands, from other repositories
implement-issue
Command "implement-issue" from outfitter-dev/blz, covering implement linear issue, context, important, preparation and workflow sequence.
review
Comprehensive code review for blz changes.
blz
Search, retrieve, and manage documentation with BLZ.
cli
Instructions: $ARGUMENTS.
docs
Instructions: $ARGUMENTS.
reset_project
Wipe the per-project memory cache for the active project when it was re-cloned from the same path.