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 sohampatwardhan/Agentic-Joplin --skill joplin-capturing-notesgit clone --depth 1 https://github.com/sohampatwardhan/Agentic-JoplinWrote 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/sohampatwardhan/agentic-joplin/joplin-capturing-notes)<a href="https://agentmods.dev/skills/sohampatwardhan/agentic-joplin/joplin-capturing-notes"><img src="https://agentmods.dev/badge/skills/sohampatwardhan/agentic-joplin/joplin-capturing-notes/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/sohampatwardhan/agentic-joplin/joplin-capturing-notes"><img src="https://agentmods.dev/badge/skills/sohampatwardhan/agentic-joplin/joplin-capturing-notes.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 | $0.00041 | $0.00659 |
| Opus 5.5 | $0.00016 | $0.00264 |
| Sonnet 5.5 | $0.00008 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
joplin-capturing-notes 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 5d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capturing notes in Joplin
See the using-joplin skill for the connection check and shared conventions (resolve
names to IDs, truncated, delete caution).
Steps
- Find the target notebook. Call
list_notebooksand match the user's intended notebook by title (use the nestedtreeto disambiguate notebooks with the same name under different parents). If it doesn't exist and the user wants it created, callcreate_notebookwith thetitleand an optionalparent_idto nest it. - Choose the format. Default to
markdown. Usehtmlonly when the content is genuinely HTML (e.g. clipped rich content). The body you pass is stored as-is in that format. - Create the note. Call
create_notewithtitle,body,format, andnotebook_id. Capture the returned noteid. - Apply tags (separate step).
create_notedoes not take tags. For each desired tag: ensure it exists vialist_tags(create it withcreate_tagif missing), then attach it withtag_note(note id + tag id). - Report the created note's id and where it landed.
Diagrams and math
Joplin renders Mermaid (```mermaid fences) and KaTeX ($...$ inline, $$...$$
display) in Markdown notes. Follow "Diagrams and math" in the using-joplin skill. In
short:
- Add a diagram or formula only when it genuinely helps (a process, architecture, sequence, or maths), never as decoration.
- If the
mermaidorkatexskill is available, use it to write the block, then embed it in thebody. If not, write a plain fence or$/$$math yourself; the capture still works. - Keep the note
formatasmarkdown(step 2); neither renders inhtmlnotes. - Verbatim captures (slides, documents, anything the user wants copied exactly): only include diagrams or formulas present in the source. Never invent or embellish one.
- You may offer to install a missing companion skill, but only run the install after an explicit yes, and don't ask again this session if they decline.
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.
- 5d ago Changed · +8 lines 7f5d2398567a
- 2mo ago First seen · 43 lines · 41 tokens per session scan A 3b62f28a509e
joplin-capturing-notes is a skill published in the GitHub repository sohampatwardhan/Agentic-Joplin (0 stars, last pushed 6d ago), licensed MIT. It adds 41 tokens to every session and 659 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 2026-09-01.
joplin-capturing-notes compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| joplin-capturing-notessohampatwardhan/Agentic-Joplin | Skill | 0 | 6d ago | MIT | A | 41 | Claude Code |
| joplinalondmnt/joplin-mcp | Skill | 174 | 1mo ago | MIT | B | 20 | Claude Code |
| deja-reflectvshulcz/deja-vu | Skill | 1.4k | today | MIT | A | 49 | Claude Code |
| specimen-authoringdylanroscover/Embody | Skill | 213 | 3d ago | MIT | A | 38 | Claude Code |
| externalize-operatordylanroscover/Embody | Skill | 213 | 3d ago | MIT | A | 22 | Claude Code |
| multi-instancedylanroscover/Embody | Skill | 213 | 3d ago | MIT | A | 23 | Claude Code |
| agent-desktop-windowsopenwong2kim/wmux | Skill | 447 | today | MIT | A | 119 | Claude Code, Codex |