A quick way to save one useful idea from the current conversation as a note in an inbox.

Use it to save a decision, discovered pattern, or connection, either inferred from the conversation or supplied as a title and body.

Writing down an insight during a discussion can interrupt the work. This captures it with little input and without a review process.

quick-note — Skill for Claude Code by robinslange/learning-loop

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add robinslange/learning-loop

Claude Code

/plugin install learning-loop

Made for: Claude Code.

Or install learning-loop, the plugin that ships this one along with the rest of its 24 skills, 20 agents, 7 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/robinslange/learning-loop/quick-note/github.svg)](https://agentmods.dev/skills/robinslange/learning-loop/quick-note)

Your own site

<a href="https://agentmods.dev/skills/robinslange/learning-loop/quick-note"><img src="https://agentmods.dev/badge/skills/robinslange/learning-loop/quick-note/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/robinslange/learning-loop/quick-note"><img src="https://agentmods.dev/badge/skills/robinslange/learning-loop/quick-note.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 869 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.

Model	Per session	Once invoked
Fable 5.1	$0.00060	$0.00869
Opus 5.5	$0.00024	$0.00348
Sonnet 5.5	$0.00012	$0.00174
Haiku 4.5	$0.00006	$0.00087

Measured 1mo ago against content hash 2492a94211cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

quick-note 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.

plugin/skills/quick-note/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quick Note: Zero-Friction Capture

Overview

Captures a single insight to 0-inbox/ mid-conversation. No preview, no approval, no multi-agent pipeline. One subagent, one note, one confirmation line.

When to Use

/learning-loop:quick-note: infer the insight from conversation context
/learning-loop:quick-note "insight as title": user provides the title
/learning-loop:quick-note "title" "body": user provides everything

Process

Step 1: Extract the Insight

If no args: Read the recent conversation. Identify the most capture-worthy insight: a decision made, pattern discovered, or connection drawn. If nothing stands out, tell the user and stop.

If title only: Use it as the insight title. Derive body from conversation context.

If title + body: Use both as provided.

Step 2: Delegate to Note Writer

Spawn a single note-writer subagent (dispatch: skills-shared/dispatch.md) with this prompt (resolve ${CLAUDE_PLUGIN_ROOT} to a literal path before dispatch — see agents-shared/vault-io.md → Placeholders):

Write a quick inbox note for the Obsidian vault.

Insight: <title>
Context: <body or conversation context summary, 2-3 sentences max>
Source project: <current project name or "conversation">
Date: <today YYYY-MM-DD>
Destination: 0-inbox/

Before writing, run this command to find related vault notes:
ll-run vault-search.mjs search "<key terms from insight>" --rerank

Use the top 1-3 relevant results as wiki-links in the note.

Write the note to its destination using the Write tool, then report the exact written path.
Return the filename, title, and the written path when done.

This is a capture, not a promotion: leave destination_locked unset so a genuinely gate-worthy note can still be promoted out of 0-inbox/ by the gate. The note may therefore land in 1-fleeting/ or 3-permanent/ rather than 0-inbox/ — so do NOT assume the folder; read the path the agent reports.

Step 2.5: Replay Post-Write Hooks

Read the full file on GitHub · 80 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.

1mo ago Changed 2492a94211cf
1mo ago Changed · -1 lines da0a537f3766
1mo ago Changed · +1 lines 46de61f5fd49
2mo ago Changed 13b41822a29b
2mo ago First seen · 80 lines · 60 tokens per session scan A a748cd3a8df2

Subscribe to this mod's changes

quick-note is a skill published in the GitHub repository robinslange/learning-loop (13 stars, last pushed 4d ago), licensed Apache-2.0. It adds 60 tokens to every session and 869 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 2026-08-30.

Memory and context

quick-note next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
quick-noterobinslange/learning-loop	Skill	13	4d ago	Apache-2.0	A	60	Claude Code
knowledge-ingestopenclaw/openclaw	Skill	394k	yesterday	MIT	A	80	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	68k	2d ago	Apache-2.0	A	217	Claude Code, Codex
forgetasgeirtj/system_prompts_leaks	Skill	71k	2d ago	CC0-1.0	A	74	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
memoryopensquilla/opensquilla	Skill	7.1k	6d ago	Apache-2.0	A	44	Claude Code, Codex
ha-data-storesshiwenwen/hope-agent	Skill	1.9k	yesterday	MIT	A	115	Claude Code, Codex