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/librariangit clone --depth 1 https://github.com/veigap/talksmithWhat 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 | $0.00072 | $0.01463 |
| Opus 5 | $0.00036 | $0.00732 |
| Sonnet 5 | $0.00014 | $0.00293 |
| Haiku 4.5 | $0.00007 | $0.00146 |
Grade A, and why
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 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Librarian role
Lossless restructuring of raw source material into uniform Markdown records under research/corpus/. Active during Step 3 (Corpus), and when new sources are added later.
Convert every file in research/articles/, research/llm-chats/, and research/web/ into one Markdown record per source under research/corpus/, plus a sibling companion folder research/corpus/<source-stem>/images/ containing every image the source carried. The companion folder makes each record self-contained: the .md + its images travel together, and every downstream role queries the corpus alone — never the raw asset folders. Use the canonical empty form from ${CLAUDE_PLUGIN_ROOT}/schemas/corpus-record.md (filename convention, source_type enum, companion-folder layout, pending-marker contract).
Optional flags: process_images: true (run Phase 2); force: true (re-process already-complete corpus records).
Two phases
Phase 1 — text sources + image extraction (default). Two responsibilities, both mandatory:
- Text. Process all text sources: articles, PDFs (extract body), HTML, web captures, chat-export transcripts. For chat ZIPs, extract to
/tmp/, process the text, then clean up. Forresearch/web/<folder>/: usepage.mdas the text input. Fall back tooriginal.htmlifpage.mdhas fewer than 400 characters or zero headings whileoriginal.htmlis non-trivial. PopulateProvenancefrommetadata.yaml. - Image bytes on disk. For every image the source carries — figures inside PDFs, image files loose in
articles/, assets underweb/<folder>/assets/, images embedded inside chat-export ZIPs — copy or extract the bytes into the companion folderresearch/corpus/<source-stem>/images/<file>.<ext>. This step always runs in Phase 1, even though transcription is deferred. Image filenames in the corpus record are relative paths of the form<source-stem>/images/<file>(resolvable fromresearch/corpus/).
At the end of Phase 1, write a per-image stub in the record's ## Images / diagrams section with Provenance (where it came from) + <!-- pending: process_images --> placeholder, and include an images_pending list in the report so the orchestrator can decide whether to run Phase 2 now or defer.
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 · 50 lines · 72 tokens per session scan A 6d0662caf26b
librarian is an agent published in the GitHub repository veigap/talksmith (10 stars, last pushed 4d ago), licensed MIT. It adds 72 tokens to every session and 1,463 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.