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 elimorals/jw-agent-toolkit --skill jw-researchgit clone --depth 1 https://github.com/elimorals/jw-agent-toolkitWrote 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/elimorals/jw-agent-toolkit/jw-research)<a href="https://agentmods.dev/skills/elimorals/jw-agent-toolkit/jw-research"><img src="https://agentmods.dev/badge/skills/elimorals/jw-agent-toolkit/jw-research/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/elimorals/jw-agent-toolkit/jw-research"><img src="https://agentmods.dev/badge/skills/elimorals/jw-agent-toolkit/jw-research.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 | $0.00048 | $0.00270 |
| Opus 5.5 | $0.00019 | $0.00108 |
| Sonnet 5.5 | $0.00010 | $0.00054 |
| Haiku 4.5 | $0.00005 | $0.00027 |
Grade A, and why
jw-research 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 1mo 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
JW research (multi-step)
Workflow for open-ended research:
- Call
search_content(query, filter_type="all", language=...)with the user's topic stripped of question framing (e.g. "what does the Bible say about peace?" → search"peace"). - For the top 2-3 results that look most relevant, call
get_article(url)to fetch the full article. - For every Bible reference mentioned in the user's question, call
resolve_referenceto get the canonical URL. - Synthesize the answer. Every doctrinal claim MUST cite a verse or article URL returned by these tools. Do not paraphrase from training data without a source.
Boundaries
- If you cannot find verified sources, say so explicitly. Do not fall back to general knowledge.
- For a single verse, prefer
jw-verse-lookup(lighter). - For meeting prep specifically, prefer
jw-meeting-prep(Phase 7).
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.
- 1mo ago First seen · 27 lines · 48 tokens per session scan A e420b0fdbe2a
jw-research is a skill published in the GitHub repository elimorals/jw-agent-toolkit (7 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 48 tokens to every session and 270 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
memobase
A Russian-language skill for searching a local knowledge base built from documents and other sources such as web pages, YouTube, audio, and Obsidian notes.
explainshell
Explain shell commands in plain English (explainshell.com).
harbor-clerk
Search and read documents from a local Harbor Clerk knowledge base. Use when the user references their personal documents, contracts, notes, emails, or asks "what did I store about X?".
teach
Explain a body of work plainly so a person actually understands it. Runs the how and why skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
how
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.
bro
Restate the last message in plain human language, with no jargon.