further

further is a skill for Claude Code, Codex from control-decks/think-it-through. It costs 50 tokens per session (389 once invoked), scanned A, original, MIT.

A focused thinking operation that extends an existing idea by one supported creative step. HACP, or the Human-Agent Control Protocol, is the method it follows for binding ideas and controlling that step.

In plain words
What is it for?
Use it when a current thought or working object has a clear edge and you want one grounded implication, combination, or possibility beyond it.
Why use it?
It helps develop an idea without restarting the discussion or expanding into unfocused brainstorming.

Skill for Claude CodeCodex

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/further
Any agent
npx skills add control-decks/think-it-through --skill further
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 further

README.md
[![agentmods](https://agentmods.dev/badge/skills/control-decks/think-it-through/further.svg)](https://agentmods.dev/skills/control-decks/think-it-through/further)
Your own site
<a href="https://agentmods.dev/skills/control-decks/think-it-through/further"><img src="https://agentmods.dev/badge/skills/control-decks/think-it-through/further.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 389 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 $0.00050 $0.00389
Opus 5 $0.00025 $0.00195
Sonnet 5 $0.00010 $0.00078
Haiku 4.5 $0.00005 $0.00039

Measured 4d ago against content hash 48b5917892de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

further 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.

plugins/think-it-through/skills/further/SKILL.md · 43 lines

What it actually says

🚀 Think Further

ID: think-it-through/further
HACP: 0.4
Kind: operation
Mode: transform
Traits: read-only, semantic, creative-extension
Default Binding: Current Working Object, then current thought
Accepts: hacp/content, hacp/result
Requires: hacp/extendable-thought
Produces: think-it-through/extended-thought
Duration: once

Effect: Find the strongest supported edge of the bound object and extend it by one non-obvious implication, combination, or possibility.

Limits: Do not scatter into broad ideation, invent evidence, restate the object, choose a direction, recommend actions, or continue beyond one leap.

Resolve the leap

  1. Recover the object's claims, evidence, constraints, and unresolved edge.
  2. Select one extension that is both non-obvious and materially connected to that edge.
  3. Preserve established claims. Mark the new part as extrapolation whenever it depends on an unverified assumption.
  4. Stop after the one useful leap.

Format

Begin the complete combo trace with > 🎯 **<binding>** → 🚀 **FURTHER** when used alone. Add → 🚀 **FURTHER** after earlier cards in a combo.

State the extension directly. Add one short Extrapolation note only when the new step depends on an unsupported assumption.

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. 4d ago First seen · 43 lines · 50 tokens per session scan A 48b5917892de

Subscribe to this mod's changes

further is a skill published in the GitHub repository control-decks/think-it-through (3 stars, last pushed 29d ago), licensed MIT. It adds 50 tokens to every session and 389 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

xiaobei-skill-academic-paper-to-ppt

Use for 小北在读研 / XiaoBei academic paper-to-PPT workflows: generate thesis-defense or project-report decks from uploaded papers, literature, reports, technical documents, and optional PPTX visual templates. Produces a source-grounded outline, an imagegen visual scheme, one complete bitmap per slide, an imagegen…

xiao24bei/xiaobei-skill · 101 tokens

animated-readme-logo

Audit, create, transform, or animate verified logo pipelines for GitHub READMEs. Use when a repository needs a new or reconstructed mark, motion specification, SVG animation master, executable animation recipe, static PNG, animated GIF, README-safe markup, reduced-motion fallback, or compatibility review. Do not use…

stark-ai-de/agent-skills · 81 tokens

poster-generator

Generates professional designer-grade posters, flyers, campaign visuals, event posters, and product posters. Use when the user asks for 海报, poster, flyer, campaign visual, event poster, product poster, promotional visual, or high-end marketing key visual.

howardz27/poster-generator-skill · 54 tokens

generate-word-clouds

Generate one or multiple weighted keyword word-cloud PNG images with confirmed brand colors, Top N selection, transparent or colored backgrounds, compact margins, horizontal text, and selectable shapes. Use when the user asks to create 词云、关键词云、品牌词云 or batch word clouds from Excel, CSV, JSON, tables, or pasted keyword…

Lucas-Fong/html-report-stable-base · 83 tokens

create-codex-theme

Create, customize, validate, locally install, and test theme packs for Codex Desktop from generated background artwork, a landscape image, brand palette, or style brief. Use when a user asks to make a Codex theme, generate or convert artwork into a Codex background/theme pack, prepare free or branded theme assets…

ViisOpen/get-codex-theme · 83 tokens

krita-control

Control a local Krita session through Krita Codex MCP. Use when Codex needs to inspect or modify Krita documents, preview canvases, manage layers, paint or draw, edit selections and colors, use undo or redo, save KRA files, export PNG files, or package animation, tileset, and named-region assets.

cyyprezz/krita-codex-mcp · 72 tokens