joplin-searching-and-updating

joplin-searching-and-updating is a skill for Claude Code from sohampatwardhan/Agentic-Joplin. It costs 41 tokens per session (567 once invoked), scanned A, original, MIT.

A workflow for finding, reading, and updating existing Joplin notes, a note-taking application's documents. It uses keyword search with optional notebook or tag filters, then updates notes by their IDs.

In plain words
What is it for?
Use it to search Joplin notes, inspect their contents and format, update selected fields, or append new material safely.
Why use it?
It reduces the risk of editing the wrong note, missing relevant results, or replacing content that should have been appended.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the agentic-joplin plugin — 4 skills, 1 MCP server shipped together

Good fit Use it to search Joplin notes, inspect their contents and format, update selected fields, or append new material safely.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sohampatwardhan/agentic-joplin/joplin-searching-and-updating
Install

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.

Any agent
npx skills add sohampatwardhan/Agentic-Joplin --skill joplin-searching-and-updating
Clone the repo
git clone --depth 1 https://github.com/sohampatwardhan/Agentic-Joplin

Made for: Claude Code.

Or install agentic-joplin, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

Wrote 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.

agentmods badge for joplin-searching-and-updating

README.md
[![agentmods](https://agentmods.dev/badge/skills/sohampatwardhan/agentic-joplin/joplin-searching-and-updating/github.svg)](https://agentmods.dev/skills/sohampatwardhan/agentic-joplin/joplin-searching-and-updating)
Your own site
<a href="https://agentmods.dev/skills/sohampatwardhan/agentic-joplin/joplin-searching-and-updating"><img src="https://agentmods.dev/badge/skills/sohampatwardhan/agentic-joplin/joplin-searching-and-updating/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.

agentmods 80×15 button for joplin-searching-and-updating

Your own site · 80×15
<a href="https://agentmods.dev/skills/sohampatwardhan/agentic-joplin/joplin-searching-and-updating"><img src="https://agentmods.dev/badge/skills/sohampatwardhan/agentic-joplin/joplin-searching-and-updating.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 567 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.00567
Opus 5 $0.00020 $0.00283
Sonnet 5 $0.00008 $0.00113
Haiku 4.5 $0.00004 $0.00057

Measured 11d ago against content hash a4856a21b039, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

joplin-searching-and-updating 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 11d 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.

packages/plugin/skills/joplin-searching-and-updating/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Searching and updating Joplin notes

See the using-joplin skill for the connection check and shared conventions.

Search is full-text, not semantic

find_notes runs Joplin's keyword full-text search — it does not understand meaning. You provide the semantic layer:

  • Start with the user's key terms; if results are thin, reformulate (synonyms, broader terms), and use the * wildcard for prefixes.
  • Scope when you can: pass notebook_id and/or tag_id to narrow.
  • Read the candidate results and judge relevance yourself rather than trusting rank.
  • If the result set comes back truncated, narrow the query or raise/lower limit deliberately — don't assume you've seen every match.

Reading

  • get_note by id returns the note; pass fields to fetch only what you need for large notes.
  • Check the returned format before editing so your edit matches the note's Markdown/HTML.

Updating and appending

  • update_note is a partial update by id — send only the fields you're changing (title, body, format, notebook_id).
  • To append rather than replace: get_note to read the current body, concatenate your addition, then update_note with the combined body in the note's existing format.
  • Be aware this read-then-write is not atomic: if the note may be edited elsewhere (the Joplin UI, sync) between your read and write, your write can clobber that change. Keep the window small and don't interleave other edits.

Enumerating

Use list_notes with notebook_id or tag_id to walk a set of notes (mind the truncated flag). Use list_note_revisions if the user wants a note's edit history.

Diagrams

Joplin renders Mermaid inside fenced ```mermaid blocks in Markdown notes. When you add a diagram to a note, or edit/fix a diagram already in one, use the mermaid skill to author and validate the Mermaid before you update_note — an unvalidated block shows as a render error in Joplin. Keep the note's existing format; Mermaid only renders when it's markdown. When appending a diagram, follow the read-then-write appending guidance above.

Read the full file on GitHub · 49 lines

Changes

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.

  1. 11d ago First seen · 49 lines · 41 tokens per session scan A a4856a21b039

Subscribe to this mod's changes

joplin-searching-and-updating is a skill published in the GitHub repository sohampatwardhan/Agentic-Joplin (0 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 567 once invoked, about $0.0002 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 2026-09-01.