distill

distill is a skill for Claude Code, Codex from onebrain-ai/onebrain. It costs 98 tokens per session (2,763 once invoked), scanned A, original, Apache-2.0.

A tool for combining notes from multiple sessions or sources about one topic into a single structured summary. It works with notes already stored in the vault.

In plain words
What is it for?
Use it to create a digest of a completed research thread, brainstorming topic, or recurring theme. For example, it can consolidate notes about a memory system, a purchase decision, or a software setup.
Why use it?
It removes the need to reread scattered notes and manually combine them. The result keeps the main ideas and relevant links together in one place.

Skill for Claude CodeCodex

Part of the onebrain plugin — 32 skills, 5 agents, 2 hooks 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 skills/onebrain-ai/onebrain/distill
Any agent
npx skills add onebrain-ai/onebrain --skill distill
Clone the repo
git clone --depth 1 https://github.com/onebrain-ai/onebrain

Made for: Claude Code, Codex.

Or install onebrain, the plugin that ships this one along with the rest of its 32 skills, 5 agents, 2 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.

agentmods badge for distill

README.md
[![agentmods](https://agentmods.dev/badge/skills/onebrain-ai/onebrain/distill.svg)](https://agentmods.dev/skills/onebrain-ai/onebrain/distill)
Your own site
<a href="https://agentmods.dev/skills/onebrain-ai/onebrain/distill"><img src="https://agentmods.dev/badge/skills/onebrain-ai/onebrain/distill.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,763 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 $0.00098 $0.02763
Opus 5 $0.00049 $0.01381
Sonnet 5 $0.00020 $0.00553
Haiku 4.5 $0.00010 $0.00276

Measured 5d ago against content hash c94fdd222c97, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

distill 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 5d 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.

.claude/plugins/onebrain/skills/distill/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Distill

Take a completed research thread, brainstorming topic, or recurring theme and compress it into a single, structured knowledge note. Unlike /wrapup (session-focused), /distill is topic-focused and spans multiple sessions.

Usage: /distill [topic]


Step 1: Identify the Topic

If a topic was provided after the command, use it directly. If not, ask:

What topic do you want to distill? (e.g. "OneBrain memory architecture", "Mac Mini purchase decision", "MCP server setup")


Step 2: Gather Source Material

Search across the vault for notes related to the topic. Use 2–3 specific keywords or phrases from the topic (prefer proper nouns and multi-word phrases over generic single words):

Use the search tools if available for content searches; Grep/Glob as fallback (when falling back to Grep, append the |mcp-miss alternation to the pattern — see SEARCH.md). For the ## Related links in the final digest (Step 5), only carry forward search-tool candidates with rerank_score ≥ 0.30 (prefer ≥ 0.60) — drop anything below 0.30 rather than linking a weak match.

  1. Session logs: Search [logs_folder]/session/**/*-session-*.md for topic keywords — extract matching ## Key Decisions, ## Action Items, ## Open Questions sections. (Post-v2.4.0: session logs live under session/ only; the -session- infix is now defense-in-depth.)
  2. Inbox: Search [inbox_folder]/*.md for related content
  3. memory/ files: Search [agent_folder]/memory/ for related entries — match topic keywords against filename and frontmatter topics: field
  4. Project/knowledge notes: Search [projects_folder]/**/*.md, [knowledge_folder]/**/*.md, and [resources_folder]/**/*.md — filter by note title or first 100 words

Report to user (N = total matches across all sources; Q = project/knowledge/resource notes combined): Found {N} sources: {M} session logs, {P} inbox notes, {Q} knowledge notes

If N = 0: Stop and inform the user: 🔴 No notes found matching '{topic}'. Try a broader keyword or check the topic name.

Read the full file on GitHub · 262 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. 5d ago First seen · 262 lines · 98 tokens per session scan A c94fdd222c97

Subscribe to this mod's changes

distill is a skill published in the GitHub repository onebrain-ai/onebrain (26 stars, last pushed 7d ago), licensed Apache-2.0. It adds 98 tokens to every session and 2,763 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

mermaid-visualizer

Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.

breferrari/obsidian-mind · 57 tokens

qmd

Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…

breferrari/obsidian-mind · 142 tokens

obsidian-cli

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…

breferrari/obsidian-mind · 102 tokens

deeppapernote

Generate a high-quality deep-reading note for a single paper and write it into an Obsidian-style vault. Use when the user gives a paper title, DOI, URL, arXiv ID, Zotero item, or local PDF and wants a polished Markdown note with strong structure, evidence-based analysis, and figure placeholders.

917Dhj/DeepPaperNote · 71 tokens

paper-glossary

Use when building reusable Obsidian glossary notes from an existing paper source manifest, optionally with a raw-sections override, especially when a reader needs a reviewed shortlist before glossary notes and article links are changed.

917Dhj/DeepPaperNote · 46 tokens

link-memory

Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.

gowtham0992/link · 0 tokens