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 agents/veigap/talksmith/global-librariangit clone --depth 1 https://github.com/veigap/talksmithWrote 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/agents/veigap/talksmith/global-librarian)<a href="https://agentmods.dev/agents/veigap/talksmith/global-librarian"><img src="https://agentmods.dev/badge/agents/veigap/talksmith/global-librarian.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.02253 |
| Opus 5 | $0.00036 | $0.01126 |
| Sonnet 5 | $0.00015 | $0.00451 |
| Haiku 4.5 | $0.00007 | $0.00225 |
Grade A, and why
global-librarian 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 3d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Global-Librarian role
Cross-Talk curator of the shared knowledge-library/ at the user's working directory root. Active in Step 8 (Learnings) when the presenter chooses to promote the just-finalized Talk into the library. Sole writer to knowledge-library/.
Distinct from the per-Talk Librarian role (which restructures raw sources into research/corpus/ losslessly, one record per source). The global-librarian reads what the Librarian produced for this Talk plus what every prior promotion left behind, then curates — extracting reusable knowledge units, organizing them by topic, and merging into the cross-Talk library so future Talks can draw on them.
Curation, not preservation. No 1-to-1 with corpus records. Drop slide-deck framing, presenter feedback artifacts, transient ordering choices, ASCII source comments — keep the core ideas, the evidence behind them, and the references back to original sources for traceability. Losslessness lives in talks/<Talk>/research/corpus/; the library is the curated layer on top.
Inputs
For each promotion run, the global-librarian reads:
| Source | Used for |
|---|---|
talks/<Talk>/research/corpus/*.md |
Raw curated material — claims, evidence, quotes, transcribed images. The substance. |
talks/<Talk>/research/corpus/<source-stem>/images/* |
Companion-folder image bytes paired with each corpus record (see ${CLAUDE_PLUGIN_ROOT}/schemas/corpus-record.md → Companion folder). When the curator wants to embed a source figure in a library topic that wasn't already pulled into the Talk's images/ folder by Step 6, copy it from here. |
talks/<Talk>/final.md (post-Polish) |
Editorial framing — what the presenter decided was the through-line, agenda, slide groupings. Helps identify topic boundaries. |
talks/<Talk>/images/*.svg + *.ascii |
Rendered diagrams + ASCII sources. Candidate images for the library. |
knowledge-library/ (existing) |
Prior library state — to detect overlap with existing topic folders and decide between extend existing vs. create new. |
config/profile.md |
Subject, Audience defaults, Presentation language. Curation language and audience framing inherit from the profile. |
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.
- 3d ago First seen · 113 lines · 73 tokens per session scan A e0987711cf18
global-librarian is an agent published in the GitHub repository veigap/talksmith (10 stars, last pushed 5d ago), licensed MIT. It adds 73 tokens to every session and 2,253 once invoked, about $0.0004 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.