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 skills add Dankaro-projects/shelfmark --skill shelfmark-manage-cataloguegit clone --depth 1 https://github.com/Dankaro-projects/shelfmarkWrote 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/skills/dankaro-projects/shelfmark/shelfmark-manage-catalogue)<a href="https://agentmods.dev/skills/dankaro-projects/shelfmark/shelfmark-manage-catalogue"><img src="https://agentmods.dev/badge/skills/dankaro-projects/shelfmark/shelfmark-manage-catalogue/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dankaro-projects/shelfmark/shelfmark-manage-catalogue"><img src="https://agentmods.dev/badge/skills/dankaro-projects/shelfmark/shelfmark-manage-catalogue.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00060 | $0.00467 |
| Opus 5 | $0.00030 | $0.00234 |
| Sonnet 5 | $0.00012 | $0.00093 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
shelfmark-manage-catalogue 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 9d 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.
What it actually says
Manage a Shelfmark Catalogue
Maintain the local catalogue without weakening its filesystem and governance safeguards.
Workflow
- Run
shelfmark --versionandshelfmark doctorto establish the installed version and current state. If Shelfmark is absent and installation is part of the request, install it withuv tool install shelfmark. - Run
shelfmark configbefore changing roots or classification rules. Treat the displayed config path as the authoritative file. - Use
shelfmark initonly when no config exists. Do not overwrite an existing config with--forceunless the user explicitly asks to replace it. - Run
shelfmark refreshafter setup or a deliberate config change. Preserve stderr in automation because refresh warnings and refusals are operational output. - Run
shelfmark reviewfirst as a dry run. Useshelfmark review --applyonly when the user wants the proposed classifications written. - Finish with
shelfmark doctorandshelfmark stats. Report the config location, indexed roots, freshness, rights split, and any unresolved finding.
Handle a Refused Refresh
- Treat a short walk or excessive-prune refusal as protection against accidental catalogue loss.
- Inspect
shelfmark doctor, the resolved roots fromshelfmark config, and filesystem availability before changing anything. - Use
shelfmark refresh --forceonly after confirming that the missing files were intentionally moved or deleted. State that this accepts the new smaller corpus and may prune catalogue rows. - Do not hide failures, discard stderr, or report a stale catalogue as healthy.
Connect the MCP Server
Prefer the plugin's bundled MCP configuration. For clients configured manually, launch shelfmark serve or the compatibility entry point shelfmark-mcp over stdio.
After connecting, call corpus_stats() to confirm that the client reaches the intended catalogue and that the index is fresh.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 31 lines · 60 tokens per session scan A fff904edad9a
shelfmark-manage-catalogue is a skill published in the GitHub repository Dankaro-projects/shelfmark (0 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 467 once invoked, about $0.0003 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 skills, from other repositories
doc-processor
A document-processing guide for creating and converting Word files, spreadsheets, presentations, Markdown, HTML, and PDFs, including extracting PDF text.
data-analyst
A guide for loading and analyzing CSV, JSON, and Excel data in memory. It covers cleaning, summaries, statistical tests, charts, time-based analysis, data-quality checks, and exporting the results.
feishu
A guide for operating Feishu, a workplace collaboration platform used for messages, documents, tasks, calendars, and groups.
pptx-html-fidelity-audit
Audit a python-pptx export against its source HTML deck, identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing), and re-export with strict footer-rail + cursor-flow layout discipline. Use this skill whenever the user has a .pptx that was generated from an…
clinical-case-report
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.