capture

capture is a skill for Claude Code, Codex from janrummel/claude-orchestrator-starter. It costs 43 tokens per session (488 once invoked), scanned A, original, MIT.

A note-taking assistant for quickly saving ideas, links, thoughts, and tasks. It can organize a note into a second brain, meaning a personal system for storing information for later use.

In plain words
What is it for?
Use it to save ideas, links, quotes, thoughts, or to-dos in an Obsidian vault, local memory, or a format you can copy. It helps title and categorize the captured note.
Why use it?
It reduces the effort needed to record something before it is forgotten. It keeps capture lightweight and can suggest categories such as projects, ongoing responsibilities, resources, or an inbox.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths.

Good fit Use it to save ideas, links, quotes, thoughts, or to-dos in an Obsidian vault, local memory, or a format you can copy. It helps title and categorize the captured note.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/janrummel/claude-orchestrator-starter/capture
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 janrummel/claude-orchestrator-starter --skill capture
Clone the repo
git clone --depth 1 https://github.com/janrummel/claude-orchestrator-starter

Made for: Claude Code, Codex.

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 capture

README.md
[![agentmods](https://agentmods.dev/badge/skills/janrummel/claude-orchestrator-starter/capture/github.svg)](https://agentmods.dev/skills/janrummel/claude-orchestrator-starter/capture)
Your own site
<a href="https://agentmods.dev/skills/janrummel/claude-orchestrator-starter/capture"><img src="https://agentmods.dev/badge/skills/janrummel/claude-orchestrator-starter/capture/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 capture

Your own site · 80×15
<a href="https://agentmods.dev/skills/janrummel/claude-orchestrator-starter/capture"><img src="https://agentmods.dev/badge/skills/janrummel/claude-orchestrator-starter/capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 488 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 $0.00043 $0.00488
Opus 5 $0.00022 $0.00244
Sonnet 5 $0.00009 $0.00098
Haiku 4.5 $0.00004 $0.00049

Measured 9d ago against content hash 26fb978fa10b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

capture 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 9d 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.

orchestrator/skills/capture/SKILL.md · 55 lines

What it actually says

Capture — Quick Note Taking

You are the intake assistant for the user's second brain. Capture thoughts instantly — no friction, no perfectionism.

Core Principles

  1. Speed over perfection — capture first, refine later
  2. Capture without judgment — everything is valid
  3. Minimal structure — a title is enough, the rest is optional
  4. Encouragement — "Captured!" not lengthy questions

Workflow

Step 1: Receive Input

  • What does the user want to save? (Idea, link, quote, thought, todo)
  • If unclear: one short question, no more

Step 2: Categorize (PARA)

Suggest a category (don't force it):

  • Project → Related to an active project
  • Area → Ongoing area of responsibility
  • Resource → Material for later use
  • Inbox → Default when unsure

Step 3: Save

Choose the best available storage:

  1. Obsidian vault (if MCP tools available) → use Obsidian MCP to create note
  2. Local memory (default fallback) → write to ~/.claude/memory/projects/ or ~/.claude/memory/decisions/
  3. Inline (if no file access) → format the note for the user to copy
  • Target folder: Inbox/ (Obsidian) or appropriate memory subdirectory
  • Format:
    # [Title]
    - **Captured:** [YYYY-MM-DD]
    - **Type:** [Idea/Note/Link/Quote/Todo]
    - **Tags:** #inbox #[context]
    
    [Content]
    
  • Confirmation: "Captured in [location]!"

Step 4: Optional — Connections

  • Related to an active project? → Offer to link
  • Relevant for other notes? → Suggest connections

Rules

  • Maximum 1 question before saving
  • Better to save in Inbox and sort later than discuss at length
  • Tone: Quick, encouraging, uncomplicated
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. 9d ago First seen · 55 lines · 43 tokens per session scan A 26fb978fa10b

Subscribe to this mod's changes

capture is a skill published in the GitHub repository janrummel/claude-orchestrator-starter (5 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 488 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 2026-08-31.

Related

Other skills, from other repositories

daily-briefing

Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…

vellum-ai/vellum-assistant · 75 tokens

wrap-session-up

End-of-session review for a Claude Code conversation. Replays what was discussed, checks for open action items, documents relevant outcomes in the brain vault, and creates Todoist tasks for anything untracked. Use at the end of a work session to ensure nothing falls through the cracks.

michaeljauk/brain-starter · 60 tokens

vault-onboarding-guide

An interactive guide for learning a file-based knowledge store with an agent. It teaches how to organize incoming material, projects, plans, tasks, logs, parked work, and resumed work.

dzhokhov/markdown-agent-vault-ru · 187 tokens

identity-snapshot

Generate a living profile of the user's working patterns, decision tendencies and quality preferences from their Dex data. Use when the user says 'what are my patterns', 'how do I work', or during week-review. Also use proactively when the model (older than 7 days) is stale. Not for planning a week; use week-plan.

davekilleen/Dex · 74 tokens

who-is-speaking

Identify the family member speaking in a shared family vault (e.g., vaulttribu), then lock the router to that vault + set auto-enrich mode to Hybrid so subsequent auto-saves route to wiki/People/ /. Companion skill for the tribu-routing convention. Trigger this skill at the start of any session on a shared…

tboome33/obsidian-mcp-router · 237 tokens

brain

Orient in the user's big-brain second brain and work brain-aware for the rest of the session. Use when the user types /brain, or asks "what am I working on", "what's on my plate", "catch me up", "what's overdue", or at the start of a session about ongoing work. Loads the vault overview, reports it in one screen, and…

jzhao234/big-brain · 87 tokens