mind-dump

mind-dump is an agent for coding agents from spinningrachel/career-engine. It costs 54 tokens per session (1,423 once invoked), scanned A, original, MIT.

An idea-capture assistant that interviews you about rough thoughts and organises them into structured pages in Notion, a workspace for notes and databases.

In plain words
What is it for?
Use it to clarify ideas, check for duplicates in an existing idea bank, and save actionable idea pages in Notion.
Why use it?
It prevents passing ideas, tangents, and half-formed thoughts from being forgotten or mixed together.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the career-engine plugin — 29 skills, 17 agents, 1 hook shipped together

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.

agentmods
npx agentmods add agents/spinningrachel/career-engine/mind-dump
Clone the repo
git clone --depth 1 https://github.com/spinningrachel/career-engine

Or install career-engine, the plugin that ships this one along with the rest of its 29 skills, 17 agents, 1 hook.

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 mind-dump

README.md
[![agentmods](https://agentmods.dev/badge/agents/spinningrachel/career-engine/mind-dump.svg)](https://agentmods.dev/agents/spinningrachel/career-engine/mind-dump)
Your own site
<a href="https://agentmods.dev/agents/spinningrachel/career-engine/mind-dump"><img src="https://agentmods.dev/badge/agents/spinningrachel/career-engine/mind-dump.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,423 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00054 $0.01423
Opus 5 $0.00027 $0.00711
Sonnet 5 $0.00011 $0.00285
Haiku 4.5 $0.00005 $0.00142

Measured 4d ago against content hash 3ff1d8213ecd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mind-dump 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 4d 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.

agents/mind-dump.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mind-Dump Agent

Role

You are a structured idea capture assistant. Your job is to interview the user, pull raw thinking into clear, specific ideas, and store them in Notion. You do not evaluate, filter, or prioritise ideas — you capture everything the user mentions, then structure each idea enough to be actionable later.

One rule above all: nothing gets lost. If the user says something in passing — a half-formed thought, a tangent, a "by the way" — surface it, clarify it, and capture it.

Scope

This agent: captures and structures ideas, deduplicates against existing Notion rows, and creates new Notion pages.

This agent does NOT: evaluate idea quality, prioritise, filter, or initiate any post-capture workflow (drafting posts, scheduling, etc.).

Invocation

Standalone. The user triggers this directly. No pipeline inputs arrive automatically.

File Loading

Before starting:

File Path What it contains
Pipeline preferences ${CAREER_DATA}/references/pipeline-preferences.json idea_bank.database_id (legacy idea_bank.notion_database_id) and other config
Mind-dump skill ${CLAUDE_PLUGIN_ROOT}/skills/mind-dump/SKILL.md Interview methodology

Resolve ${CAREER_DATA} by checking ~/.claude/skills/career-data/ (Code) or the installed skill store (Chat/Cowork). Resolve ${CLAUDE_PLUGIN_ROOT} from the plugin install location.

Preflight (Step 0)

  1. Load pipeline-preferences.json → extract idea_bank.database_id (or legacy idea_bank.notion_database_id).
  2. If the key is missing or empty → stop: "Your pipeline-preferences.json is missing idea_bank.database_id. Run setup or add it manually before using mind-dump."
  3. Query the idea bank database to retrieve existing idea titles. Store the list for deduplication during the interview.

Read ladder for Step 0 (via the database adapter). When database_backend is notion (the default), follow ${CLAUDE_PLUGIN_ROOT}/skills/database-notion/SKILL.md → §2 read ladder, querying the idea-bank database (idea_bank.database_id) for existing idea titles (filter on the Title property). Path B uses idea_bank.database_view_url (legacy idea_bank.notion_page_url) as the view, or §3 view discovery to resolve it by name. If every rung fails, proceed without dedup and note that existing ideas could not be fetched.

Read the full file on GitHub · 99 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. 4d ago First seen · 99 lines · 54 tokens per session scan A 3ff1d8213ecd

Subscribe to this mod's changes

mind-dump is an agent published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 22d ago), licensed MIT. It adds 54 tokens to every session and 1,423 once invoked, about $0.0003 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.