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/utilizegit 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 | $0.00022 | $0.00755 |
| Opus 5 | $0.00011 | $0.00378 |
| Sonnet 5 | $0.00004 | $0.00151 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
utilize 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run exactly one iteration of LibrAIum's utilization loop. Where /improve hardens what exists, /utilize builds the mechanisms that make the library earn its keep: commands, agents, skills, scripts, MCP tools, docs. One iteration = one deliverable, proven useful, verified, committed.
P — Plan
Read .claude/utilization-backlog.md and pick the highest-priority pending item that fits one focused session. If the top item is too big, split it and take the first piece. State what you picked and the utilization payoff you expect.
If the backlog is missing or Pending is empty: run a fresh ideation pass over these personas — new-project developer, maintainer/curator, Claude Code integration, batch automation (user-invoked only), publisher, decision support — and refill Pending with concrete, single-commit-sized items before picking. If ideation surfaces nothing that genuinely clears the value bar, write ## LOOP COMPLETE at the top of the backlog and stop honestly.
D — Do
Build the deliverable. Hard constraints (override anything the backlog says):
- FORBIDDEN future phases: X/Twitter auto-collection, semantic search / embeddings, project bootstrap generation (scaffolding). Lexical techniques only.
- Fully local & private. GitHub API (
gh) only inside explicitly user-invoked actions — never a daemon, never a scheduled network call. - No new runtime dependencies unless the item is impossible without one; justify in the commit message.
- Data-format changes touch BOTH implementations (
src-tauri/src/⇔mcp-server/lib/store.js) plus a conformance fixture — see/format-sync. - New entries follow the
entry-authoringskill; UI changes followDESIGN.md. - Match existing idiom; if commands/scripts/structure changed, update CLAUDE.md and README in the same commit.
C — Check
Two gates, both required:
- The acceptance check from the backlog item — actually exercise the deliverable (run the command, invoke the script on real data, query the MCP tool) and show the observable result. A tool nobody ran is not done.
bash scripts/verify-all.sh— all stages green. Fix root causes, not tests. For non-trivial diffs, havelibraium-reviewerreview before committing.
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 · 40 lines · 22 tokens per session scan A 2e458a50131f
utilize is a command published in the GitHub repository nel-neru/LibrAIum (0 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 755 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
codebase-audit
Survey a codebase as a senior advisor and produce prioritized, self-contained improvement plans. Read-only on source code. Use standalone before iteration-start to discover what's worth doing, or independently to build a prioritized backlog.
memory-update
Run the Memory Update protocol. Checks whether decisions, questions, assumptions, risks, tasks, or opportunities emerged in the current task and writes them to the right files, then prints the required end-of-task summary.
reconcile
Clear the decision review backlog. Walk the decisions that are due for review and, for each, decide together: still true, needs evidence, changed, or archive.
queue
"What's coming up — plan steps, releases, backlog, and overdue decisions?".
status
Show wiki state at a glance — counts, recent activity, index drift, inbox backlog, collectionPurpose coverage, Core Context snapshot age.
decompose
Feature/story breakdown — consume a ready-for-decompose scope doc and produce a task graph in the issue tracker. Re-entrant; tracker-as-canonical with vault breadcrumb.