Xpansion Framework

AI at full power.
With something holding it to account.

You use Claude Code to build real things — software, campaigns, research, systems. XF enforces the full contract: intent defined before work begins, violations caught before they ship, delivery verified against what you actually specified, and a memory that compounds across every session. Whatever you're building, the ceiling is yours.

Connect with GitHub — it's free See how it works →

10-day free trial — full Pro  ·  Founding Pro: $6/mo  ·  Team: $12/seat/mo

● ● ●
● Xpansion Framework  ready

Anyone who builds with AI knows this feeling.

It's not a skill problem. It's a structural one. The model is powerful — and completely unaccountable.

It said it was done. It wasn't.

Claude reports success. The output looks right. Three steps later, something is broken — or missing — and tracing it back costs more time than the original task. There was no checkpoint. There was no verification. There was just trust.

Change one thing. Break three others.

Nothing in the model knows what depends on what. A change lands. Something else breaks. Fix that — something else breaks. The loop has no natural exit unless something outside the model is tracking the connections.

The session ends. So does everything in it.

The decision you landed on. The tradeoff you reasoned through. Why you chose this approach. Gone. Tomorrow you start from the beginning — not from where you were.

Xpansion was built by someone who lived this — not an observer diagnosing from the outside, but a builder inside the loop. The frustration isn't unique to developers. It belongs to anyone building real things with AI: products, content, systems, decisions. Powerful tools. No accountability layer. Until now.

This is built for them.

Three things you stop worrying about.

Did it do what I meant?

XFFI defines your intent as a finite, verifiable spec before work begins. XFXA checks every terminal before you ship. You stop guessing and start knowing.

What did I miss?

XFFI's discovery phase asks the questions about your brief that you didn't know to ask. Boundaries surface before work begins — not after something breaks.

Where was I?

XFMT builds a memory tree that compounds across every session. Every decision, every context, every tradeoff — searchable, permanent, always carried forward.

Whatever you're building, XF runs the same enforcement.

XF started in code. It didn't stay there. The thesis — code enforces what the LLM can't be counted on to do alone — applies anywhere AI is doing structured work. The four session modes map to any domain.

Code
Build

Implementation, debugging, refactoring. Contract violations caught before they land. Blast radius mapped before you commit.

Create
Understand

Writing, product definition, design. Intent defined as deliverables. Verified against what was actually produced.

Concept
Specify

Research, architecture, strategic analysis. Design decisions formally specified. Grounded in verified data, not inference.

Operate
Operate

Deployment, configuration, incident response. System state verified. Changes tracked against intended configuration.

The only limitation is the scope of what you're trying to accomplish.

Seven modules. One tree.

Intent defined. Execution enforced. Delivery verified. Memory compounded. Seven modules — six enforcement roots feeding upward into XFMT, all anchored by your vision below.

XF Finite Intent
XFFI

Before any work starts, XFFI decomposes your intent into a finite MECE spec — grounded in what already exists (Roots), decomposed into binary-verifiable terminals across four domains: Build, Understand, Specify, Operate. Works for code, content, research, or system configuration. Every module that follows executes against this spec.

Full breakdown →
XF Tool Dispatch
XFTD

Every task shift, Xpansion scans 16,500+ MCPs, plugins, and skills — ranked against your actual stack — and surfaces the right one. Claude only sees what's installed. XFTD sees everything.

Full breakdown →
XF Boundary Auditor
XFBA

Every edit hits an enforcement gate. Wrong type, missing import, broken caller — caught before it lands. Not flagged after the fact. Stopped at the moment it would have shipped. The "my bad" loop ends here.

Full breakdown →
XF System Impact Auditor
XSIA

One thing changes. XSIA maps every caller, every dependent, every downstream path — before any change lands. You see the full blast radius. Then decide.

Full breakdown →
XF Token Control
XFTC

Context fills silently. XFTC nudges at 60%, gates at 85%. Your session — your call. Every snapshot preserves everything before it's gone. Nothing lost to a silent compact.

Full breakdown →
XF Xecution Assurance
XFXA

What you intended and what Claude built are not the same thing. XFXA checks — mechanically, not by trusting the model — before anything ships. Binary: met or not met. No ambiguity.

Full breakdown →
Capstone — XF Memory
XFMT

Not your project's memory. Yours — across every project you've ever touched in Claude Code. XFFI defines the intent. The other five modules enforce it. XFMT remembers everything: every decision, every enforcement, every verified terminal. The tree grows organically from your conversations — no folders, no tags, no maintenance. The longer it runs, the more it knows. The more it knows, the less you have to explain.

Full breakdown →
◈ XFMT ✓ session saved
247 turns · ~/.claude/xfmt/snapshots/
$ /xfmtr "flutter oauth redirect"
↳ 2026-03-21 — OAuth redirects to /dashboard, not /
↳ 2026-04-01 — Supabase session timeout set to 7 days
255 sessions · growing

Three things only XF does.

Other Claude Code frameworks give Claude more skills. More things it can reach for. XF is the layer between you and the mistake — the enforcement, the routing intelligence, and the memory that compounds.

Tool Routing
16,500+ tools. AI-classified. Real time.

Other frameworks surface a fixed skill catalog. XF routes across 16,500+ MCPs, plugins, and skills using AI intent detection — matched to your task and your stack, on every shift, without you asking.

Enforcement
The only layer that catches breaks before they land.

XFBA catches code contract violations at edit time. XSIA maps what else breaks before you commit. Other tools help you ship faster. XF ensures what you ship doesn't take down something else on the way out.

Memory Tree
A tree that grows. Not a log that accumulates.

XFMT builds an organic memory tree — each concept finds its branch, decisions surface with temporal precision, contradictions flagged automatically. Every session makes the tree smarter. Nothing is ever lost.

Not a feature set. A communication protocol.

Most AI tools add capabilities. Xpansion Framework adds structure — the missing layer between AI-generated output and verified execution.

Finite Boundary

Every session begins with a defined boundary — what this task is, what it touches, and what it must not break. XFBA and XSIA enforce the edges. The AI doesn't guess where the walls are. They're defined.

Recursive Discovery

From every change, XF maps every branch — every caller, every dependency, every downstream effect. Not a static checklist. A live graph that updates as Claude Code works, surfacing what you didn't know to ask about.

Terminal

Nothing ships without a terminal — a binary, verifiable outcome that defines what done actually means. Not a feeling. Not a test that passed once. A finite result, enforced by XFXA before every commit.

This is the structure that makes Human-to-AI communication reliable at scale. Boundaries contain the blast radius. Recursive discovery surfaces what's hidden. Terminals replace assumption with verification. Together, they make Claude Code something you can deliver with confidence — not just speed.

The only limit is what you set out to build.

XF enforces intent. It doesn't care what domain that intent lives in.

Code

"I finally shipped without second-guessing it. XFXA said 9 of 9 terminals met. That was my sign-off."

A founder building their first product. XFFI defined every deliverable before a line was written. XFBA caught violations at edit time. XFXA confirmed everything before push. No more "I think it's done."

Create

"I briefed Claude on a 12-piece campaign. Two weeks later, every deliverable traced back to the original brief — not what felt right in the moment."

A marketer running a product launch. XFFI scoped the campaign before Claude wrote a word. XFMT carried the brief across every session. Nothing drifted.

Concept

"Every claim in the report was traceable to data we actually had. XFFI wouldn't let a terminal reference anything we hadn't confirmed."

A researcher synthesizing a complex analysis. Roots grounded the spec in real data sources. No hallucinated citations. No drifting into inference. Grounded work from the first terminal.

Operate

"Nothing advanced until the previous phase was confirmed. We ran a zero-downtime migration across three environments with no surprises."

An ops team running a critical production deployment. XFFI defined the phase gates. XSIA mapped what would break if sequence was violated. Every step earned the next one.

These are four worlds. The enforcement is the same in all of them. XF doesn't know what you're building — it only knows how to make sure you delivered what you intended. The scope of what it can enforce is bounded by exactly one thing: your vision.

Start free. Stay protected.

Three tiers. One mission: verified execution, every session.

10-day free trial
Start Free
Full Pro access for 10 days — no card required
$0 / to start
  • All 7 modules during trial
  • Unlimited detections
  • XFMT + XFXA included
After 10 days, stays free with:
  • 5 tool detections/day (XFTD)
  • XFTC context monitoring
  • XFBA basic checks
Start free trial →
Team
For teams shipping with Claude Code
$12 / seat / mo
Minimum 3 seats
  • Everything in Pro
  • Team dashboard
  • Usage analytics across team
  • Admin controls
  • Priority support
Contact us →

Common questions

What is Xpansion Framework?
Xpansion Framework is a seven-module enforcement layer for Claude Code. XFFI defines intent as a finite MECE spec — grounded in verified Roots, decomposed into four limbs — before work begins. Six modules execute against that spec: XFTD routes to the best tool from 16,500+ options, XFBA catches contract violations before edits land, XSIA maps cascade impact before any change is committed, XFTC monitors context and token usage, XFXA verifies delivery against the original spec, and XFMT builds a living memory tree that compounds across every session. All run automatically as hooks — for any type of work: Code, Create, Concept, or Operate.
How is Xpansion Framework different from Claude Code plugins or skills?
Plugins and skills give Claude new capabilities. Xpansion Framework protects the session itself — it's the guardrail layer that runs before and after every tool call, not a tool Claude reaches for. You install both; they serve different purposes.
Does it work with any Claude Code project?
Yes. XF is language and framework agnostic — it works with any stack Claude Code supports. Stack detection auto-configures tool recommendations for your specific project.
Does XF only work for software development?
No. XF works for any Claude Code session — writing (Create mode), research and analysis (Concept mode), deployment and configuration (Operate mode), and software development (Code mode). XFFI classifies your intent at the start of every session and routes to the right mode automatically. XFBA, XSIA, XFMT, and XFXA work the same way regardless of what you're building.
Is Xpansion Framework open source?
The core framework is MIT licensed and available on GitHub. The hosted service adds catalog network intelligence — pre-ranked tools built from real install patterns across thousands of developers — which can't be self-hosted.
How does the 10-day free trial work?
Sign up with GitHub — no card required. You get full Pro access for 10 days: all seven modules, unlimited detections, XFMT, and XFXA. After 10 days your account stays free permanently with unlimited XFTD routing, XFTC monitoring, and basic XFBA.
What happens after the free trial ends?
Your account drops to the free tier automatically — no action needed, nothing gets deleted. You keep 5 tool detections per day (XFTD) and XFTC context monitoring. Upgrade to Pro anytime to restore the full suite including XFMT, XFXA, and unlimited detections. Founding members lock in at $6/mo for life.
How does XFMT prevent context loss?
XFMT grows an organic memory tree — every concept from every session is decomposed, placed in its branch, and retrievable with temporal precision. XFTC nudges at 60% to snapshot and compact. At 85% an enforcement block fires — snapshot, compact, or continue with eyes open. Disk snapshots are always written locally. Semantic search across the tree requires your own pgvector database (Supabase, Neon, or any Postgres+pgvector host — your data never touches Dispatch servers).
How does XF compare to Claude Code skill frameworks?
Skill frameworks give Claude more things it can do — more skills to reach for. XF is the enforcement and routing layer between you and the mistake. XFBA catches code contract violations before they ship. XSIA maps cascade impact before you commit. Dispatch routes across 16,500+ tools by AI intent detection. XFMT grows a living memory tree. These capabilities don't exist in skill frameworks — most XF users run both. They serve different purposes.
Does Xpansion Framework slow down Claude Code?
XFTD classification runs in ~100ms on every message. Pre-tool interception adds <200ms on Pro (catalog is pre-ranked, no LLM at hook time). The 10-second hard timeout enforced by Claude Code means XF can never hang your session.
How do I install it?
git clone https://github.com/XpansionFramework/Dispatch && cd Dispatch && ./install.sh Takes about two minutes. Start a new Claude Code session after install.

Your vision is the only limit.

Code, content, research, deployment — XF enforces the full contract, whatever you're building. One install. Every session. Automatically. The ceiling is yours.

Connect with GitHub — it's free