distill

distill is a skill for Claude Code, Codex from control-decks/think-it-through. It costs 52 tokens per session (444 once invoked), scanned A, original, MIT.

A command that separates and clarifies fragmented, implied, or difficult-to-express thoughts. It shows relationships only when the available context supports them.

In plain words
What is it for?
Use it before answering when a thought needs clarification, especially when several ideas may be related but their dependencies or differences are unclear.
Why use it?
It helps turn a muddled request or idea into distinct, understandable parts without adding advice, conclusions, or unsupported connections.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present.

Part of the think-it-through plugin — 17 skills 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/control-decks/think-it-through/distill
Any agent
npx skills add control-decks/think-it-through --skill distill
Clone the repo
git clone --depth 1 https://github.com/control-decks/think-it-through

Made for: Claude Code, Codex.

Or install think-it-through, the plugin that ships this one along with the rest of its 17 skills.

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/control-decks/think-it-through/distill.svg)](https://agentmods.dev/skills/control-decks/think-it-through/distill)
Your own site
<a href="https://agentmods.dev/skills/control-decks/think-it-through/distill"><img src="https://agentmods.dev/badge/skills/control-decks/think-it-through/distill.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 444 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 5.1 $0.00052 $0.00444
Opus 5 $0.00026 $0.00222
Sonnet 5 $0.00010 $0.00089
Haiku 4.5 $0.00005 $0.00044

Measured 6d ago against content hash 5b37c00a6e26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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/think-it-through/skills/distill/SKILL.md · 52 lines

What it actually says

🧪 Think Distill

ID: think-it-through/distill
HACP: 0.4
Kind: operation
Mode: transform
Traits: read-only, semantic
Default Binding: Latest human message in relevant context
Accepts: hacp/content, hacp/result
Produces: think-it-through/clarified-thought
Duration: once

Effect: Separate every material thought, clarify each one, and expose only convergence, tension, or dependency supported by the bound context.

Limits: Preserve meaning, ambiguity, and distinctions. Do not invent connections, add advice, choose a direction, or replace clarification with another effect.

Flow

flowchart LR
    A["Latest message in context"] --> B["Separate material thoughts"]
    B --> C["Clarify each thought"]
    C --> D{"Relationship supported?"}
    D -->|Yes| E["Show connection or tension"]
    D -->|No| F["Keep thoughts distinct"]
    E --> G{"Reading still ambiguous?"}
    F --> G
    G -->|Yes| H["Show readings and ask once"]
    G -->|No| I["Respond or pass result"]

Format

Begin the combo trace with > 🎯 **<binding>** → 🧪 **DISTILL**, then use:

  1. Distilled with one formulation or a short list.
  2. Connections only when the context supports them.
  3. Response when used alone, stating the remaining question or asking one necessary clarification.

Keep advice and direction out of Response. Add later operation cards with ; show the trace once for the complete combo.

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 52 lines · 52 tokens per session scan A 5b37c00a6e26

Subscribe to this mod's changes

distill is a skill published in the GitHub repository control-decks/think-it-through (3 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 444 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.

Related

Other skills, from other repositories

codex-delegate

Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Codex — phrasings like "have Codex do X", "delegate this to Codex", "run it through Codex", or "use Codex to implement/fix/refactor" …

amElnagdy/delegate-skills · 155 tokens

commandcode-delegate

Delegate a coding task to the Command Code CLI (cmd) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Command Code — phrasings like "have Command Code do X", "delegate this to commandcode", "run it through cmd", or "use Command Code…

amElnagdy/delegate-skills · 123 tokens

warp-delegate

Delegate a coding task to the Warp Agent CLI (oz) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Warp - phrasings like "have Warp implement X", "delegate this to the Warp CLI", "run it through Warp", "use oz to…

amElnagdy/delegate-skills · 144 tokens

claude-delegate

Delegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, then review its diff and land it yourself. Use only when the user explicitly asks to delegate implementation to Claude Code, another Claude session, or the claude CLI — for example, "have another Claude implement…

amElnagdy/delegate-skills · 117 tokens

cursor-delegate

Delegate a coding task to the Cursor Agent CLI (cursor-agent) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Cursor — phrasings like "have Cursor implement X", "delegate this to Cursor", "run it through Cursor Agent", or "use…

amElnagdy/delegate-skills · 120 tokens

zcode-delegate

Delegate a coding task to the Z.AI ZCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to ZCode — phrasings like "have ZCode do X", "delegate this to ZCode", "run it through ZCode", or "use ZCode to implement/fix/refactor" — or…

amElnagdy/delegate-skills · 124 tokens