insight

insight is a command for Claude Code from technicalpickles/pickled-claude-plugins. It costs 9 tokens per session (1,112 once invoked), scanned A, original, MIT.

A command that saves an insight from the current conversation into the inbox of an Obsidian vault, a folder of linked Markdown notes. The note is kept raw until a later processing step.

In plain words
What is it for?
Use it to capture a supplied insight, or to save a useful idea from the current conversation for later sorting and linking.
Why use it?
It lets you record an idea immediately without interrupting the conversation to organise or connect it.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the second-brain plugin — 11 skills, 7 commands shipped together

Good fit Use it to capture a supplied insight, or to save a useful idea from the current conversation for later sorting and linking.

Compare 6 commands from other repositories ↓
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 technicalpickles/pickled-claude-plugins
Claude Code
/plugin install second-brain

Made for: Claude Code.

Or install second-brain, the plugin that ships this one along with the rest of its 11 skills, 7 commands.

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 insight

README.md
[![agentmods](https://agentmods.dev/badge/commands/technicalpickles/pickled-claude-plugins/insight/github.svg)](https://agentmods.dev/commands/technicalpickles/pickled-claude-plugins/insight)
Your own site
<a href="https://agentmods.dev/commands/technicalpickles/pickled-claude-plugins/insight"><img src="https://agentmods.dev/badge/commands/technicalpickles/pickled-claude-plugins/insight/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 insight

Your own site · 80×15
<a href="https://agentmods.dev/commands/technicalpickles/pickled-claude-plugins/insight"><img src="https://agentmods.dev/badge/commands/technicalpickles/pickled-claude-plugins/insight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,112 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 $0.00009 $0.01112
Opus 5.5 $0.00004 $0.00445
Sonnet 5.5 $0.00002 $0.00222
Haiku 4.5 $0.00001 $0.00111

Measured 10d ago against content hash 57ad3edd90a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

insight 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 10d 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.

plugins/second-brain/commands/insight.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capture Insight

Capture an insight from the current conversation to your Obsidian vault inbox.

This command captures raw insights quickly. Processing, routing, and connection discovery happen later via /second-brain:process-inbox.

Step 1: Load Configuration

Load configuration using sb CLI:

npx @techpickles/sb config default    # Get default vault name
npx @techpickles/sb config vaults     # List all configured vaults

If sb is not available, inform user:

sb CLI is required but not available. Install Node.js and npm, then try again.
Or install globally for faster execution: npm i -g @techpickles/sb

If no vaults are configured, inform user:

Second brain not configured. Run /second-brain:setup first.

Use the symlink path ~/.claude/vaults/{name} to access the vault for reading CLAUDE.md (e.g., ~/.claude/vaults/primary).

Read vault's CLAUDE.md for structure rules.

Load skill references:

  • second-brain:obsidian for tool mechanics
  • references/sb-cli.md for sb invocation details
  • references/zettelkasten.md for naming

Step 2: Identify the Insight

If argument provided: Use the argument as the insight to capture.

If no argument: Ask: "What insight would you like to capture?"

Also review recent conversation context to suggest what might be worth capturing.

Step 3: Create or Append to Session Notes

Session notes files collect all insights from a conversation in one place, with cheap metadata attached at capture time.

Check if session file already exists in this conversation.

If this is the first /insight command in this conversation:

  1. Create a new session notes file using sb CLI:
npx @techpickles/sb note create \
  --source auto \
  --title "{session context}"

Generate the title from conversation context: repo name, current branch, work item ID if your context names one, and what you're working on (e.g., "Debugging auth timeout in zenpayroll").

The file is created with frontmatter. Read the created file to preserve the exact frontmatter sb wrote.

Read the full file on GitHub · 138 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. 10d ago Changed 57ad3edd90a0
  2. 1mo ago First seen · 138 lines · 9 tokens per session scan A 98f53a378b01

Subscribe to this mod's changes

insight is a command published in the GitHub repository technicalpickles/pickled-claude-plugins (11 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 1,112 once invoked, about $0.0000 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.