Is the Future Tokens - Reasoning Instruments skill free?

Yes. The skill itself is free from jordanrubin/FUTURE_TOKENS. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Future Tokens - Reasoning Instruments SkillProof Score?

8.0/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Future Tokens - Reasoning Instruments?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Future Tokens - Reasoning Instruments with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Future Tokens - Reasoning Instruments

Ten composable reasoning operators to surface an AI output's blind spots

by jordanrubin · jordanrubin/FUTURE_TOKENS

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.0/10
Tested: Jul 25, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · dceea43

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 25, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Ten composable reasoning operators, each with a detailed procedural body rather than vibes. Ran negspace on a 'strategic realignment' memo versus a plain no-skill read: the baseline reached the obvious 'this means layoffs,' but negspace additionally surfaced distinct, class-tagged shadows the baseline missed - an optionality omission (no teams or timelines named, to keep maneuverability) and an unstated shareholder-primacy bedrock. The 'works every time' reliability claims are aspirational, but the sub-skill files are genuinely structured. Note the repo's own install.sh registers the ten operators as separate skills and slash-commands; the verified command below installs the whole collection under one slug, keeping the operator files reachable from the root index.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 4/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Future Tokens - Reasoning Instruments does

A collection of ten named, composable reasoning operators - negspace, excavate, antithesize, dimensionalize, synthesize, and more - each targeting a specific blind spot in an AI-generated draft. Use it after producing an analysis, plan, or recommendation to surface missing arguments, hidden assumptions, the strongest counter-case, or dimensions you are not scoring on. Each operator ships a detailed procedural definition with worked examples and chains into the others.

How to install Future Tokens - Reasoning Instruments

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Future Tokens - Reasoning Instruments

/future-tokens Ten composable reasoning operators to surface an AI output's blind spots

It also activates on plain-language prompts like these:

Run negspace on this strategy memo to find what's missing
What blind spots am I not seeing in this recommendation?
Antithesize this plan and give me the strongest counter-case

Frequently asked questions

Is the Future Tokens - Reasoning Instruments skill free?: Yes. The skill itself is free from jordanrubin/FUTURE_TOKENS. SkillProof publishes the install command and an independent test verdict at no cost.
Does Future Tokens - Reasoning Instruments work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 25, 2026. Verdict: Tested · Works. Ten composable reasoning operators, each with a detailed procedural body rather than vibes. Ran negspace on a 'strategic realignment' memo versus a plain no-skill read: the baseline reached the obvious 'this means layoffs,' but negspace additionally surfaced distinct, class-tagged shadows the baseline missed - an optionality omission (no teams or timelines named, to keep maneuverability) and an unstated shareholder-primacy bedrock. The 'works every time' reliability claims are aspirational, but the sub-skill files are genuinely structured. Note the repo's own install.sh registers the ten operators as separate skills and slash-commands; the verified command below installs the whole collection under one slug, keeping the operator files reachable from the root index.
What is the Future Tokens - Reasoning Instruments SkillProof Score?: 8.0/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Future Tokens - Reasoning Instruments?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Future Tokens - Reasoning Instruments with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.