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 cboulanger/zotero-skills --skill zotero-plugin-devgit clone --depth 1 https://github.com/cboulanger/zotero-skillsWrote 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/cboulanger/zotero-skills/zotero-plugin-dev)<a href="https://agentmods.dev/skills/cboulanger/zotero-skills/zotero-plugin-dev"><img src="https://agentmods.dev/badge/skills/cboulanger/zotero-skills/zotero-plugin-dev/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/cboulanger/zotero-skills/zotero-plugin-dev"><img src="https://agentmods.dev/badge/skills/cboulanger/zotero-skills/zotero-plugin-dev.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 | $0.00235 | $0.03312 |
| Opus 5.5 | $0.00094 | $0.01325 |
| Sonnet 5.5 | $0.00047 | $0.00662 |
| Haiku 4.5 | $0.00023 | $0.00331 |
Grade A, and why
zotero-plugin-dev 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 7d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zotero plugin development
Zotero plugins are privileged, bootstrapped Mozilla add-ons: they run with full chrome
access (XPCOM, file system, the whole Zotero object) and can be enabled, disabled and
upgraded without a restart. That combination is where most bugs come from — a plugin
that works on first install but leaks UI, listeners or memory when it is disabled,
upgraded or when the main window is reopened. Much of this skill is about keeping
startup and teardown symmetrical.
Model knowledge of Zotero plugins is often stale (Zotero 6 overlays, install.rdf,
chrome.manifest, Services.jsm imports, Bluebird, single-collection selection). Trust
this skill and the official "Zotero N for Developers" pages over recall.
0. Establish the target first
Before writing code, pin down:
- Zotero versions to support. Current stable is 10 (Firefox 140 ESR base, same as 9).
Zotero 8 moved to Firefox 140 and ESM-only; Zotero 10 changed selection, search,
full-text and local-API behavior. Read
references/version-changes.mdwhenever the plugin must run on more than one major version or is being ported. - Scaffold. Two sensible paths:
- Plain JS, no build step — copy
assets/minimal-plugin/(modeled on the official Make It Red 2.0 sample). Best for small plugins, bridges, or when the user wants to understand every line. - TypeScript + hot reload — windingwind's
zotero-plugin-templatewithzotero-plugin-scaffold,zotero-plugin-toolkitandzotero-types. Best for anything with real UI or ongoing development. Seereferences/template-workflow.md. If the user already has a repo, follow its structure; don't migrate scaffolds unasked.
- Plain JS, no build step — copy
- Plugin ID (
name@domain), a short namespace prefix (used for element IDs, Fluent IDs, pref keys, CSS classes), and the pref branch (extensions.<namespace>.*orextensions.zotero.<namespace>.*).
1. Anatomy
my-plugin/
├── manifest.json # WebExtension-style metadata; applications.zotero is mandatory
├── bootstrap.js # lifecycle + window hooks
├── prefs.js # default prefs, plugin root (NOT defaults/preferences/)
├── my-plugin.js # main code, loaded via Services.scriptloader.loadSubScript
├── preferences.xhtml # optional pref-pane fragment (no DOCTYPE, XUL default ns)
├── style.css
└── locale/en-US/my-plugin.ftl # Fluent; auto-registered, no chrome.manifest needed
What ships with it
15 files 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.
- assets/minimal-plugin/bootstrap.js 888 B runs code
- assets/minimal-plugin/locale/en-US/my-plugin.ftl 134 B
- assets/minimal-plugin/manifest.json 337 B
- assets/minimal-plugin/my-plugin.js 2.6 KB runs code
- assets/minimal-plugin/preferences.xhtml 361 B
- assets/minimal-plugin/prefs.js 63 B runs code
- assets/minimal-plugin/style.css 77 B
- evals/evals.json 1.8 KB
- references/data-api.md 8.5 KB
- references/dialogs.md 4.6 KB
- references/plugin-apis.md 8.1 KB
- references/template-workflow.md 2.4 KB
- references/toolkit.md 14 KB
- references/version-changes.md 4.7 KB
- scripts/build_xpi.py 2.7 KB runs code
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.
- 7d ago First seen · 228 lines · 235 tokens per session scan A a16e8089104a
zotero-plugin-dev is a skill published in the GitHub repository cboulanger/zotero-skills (3 stars, last pushed 7d ago), licensed CC0-1.0. It adds 235 tokens to every session and 3,312 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-09-24.
Other skills, from other repositories
bids
Use this skill when working with Brain Imaging Data Structure (BIDS) datasets: organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, motion capture, EMG, MR spectroscopy, behavioral), querying BIDS layouts, validating compliance, converting DICOM to BIDS, writing metadata sidecars…
gget
Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST/BLAT, viral sequence downloads, AlphaFold structures, enrichment analysis, OpenTargets, COSMIC, CELLxGENE, and 8cube mouse specificity/expression data. Best for interactive exploration and simple queries. For batch…
optimize-for-gpu
GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial, and RAFT. Use whenever the user mentions GPU/CUDA/NVIDIA acceleration, or wants to speed up NumPy, pandas, scikit-learn, scikit-image, NetworkX, GeoPandas, or Faiss workloads. Covers physics…
rowan
Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflows, and related…
benchling-integration
Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps, and Data Warehouse queries. Use when automating lab data with benchling-sdk or the v2 API.
pymoo
Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.