Claude gets the task. Maxim's router classifies it, sends it to the right office, loads the behavioral framework, runs the compliance gate, and tags the output with a confidence rubric. Hover any office below to see who that office dispatches to.
Hover any office to see the specialists that office dispatches to. Seven offices · 91 agents · one router.
Six reasons operators who use Claude every day install Maxim on day one. Each reason has a behavioral science framework behind it: footnoted, not shouted.
A failed compliance audit. A brand voice that slips in a prospect email. A product spec that hallucinates a library. A pricing page that contradicts the contract. These cost real money, real trust, and real time to unwind. $19.99/month is what most teams spend on coffee for a week.
Framework: Prospect Theory (Kahneman & Tversky, 1979) →Paste the install command. Hit Enter. Your very next output comes back with a confidence tag, a cited framework, and an audit trail. No retraining, no new workflow, no handoff between tools. You keep using Claude Code exactly the way you already do: the outputs just come out better.
Framework: COM-B (Michie, van Stralen & West, 2011) →Generic Claude hands you confident prose. Maxim hands you prose plus the behavioral mechanism it applied and the anti-patterns it avoided. You evaluate the output against the claim. You can defend it to your boss, your customer, or a regulator. It stops being a chat. It starts being documentation.
Read the ADR: Behavioral Moat Framing Doctrine (ADR-007) →Every Maxim response ends with a four-line rubric: what grounds this answer, what is missing, what you should do to close the gap, what would move the confidence up or down. You stop guessing when to trust the model. Trust becomes a property of the output, not a property of your mood.
Framework: Technical Educator Rubric (ADR-010) →Starter is free forever. Not crippleware. Not a 30-day trap. A regression test in our build fails the release if the free tier ever silently narrows. Start free. Upgrade when the moat shows up in your work. Cancel any time.
Read the ADR: Reciprocity (Cialdini, 2001) + ADR-004 →Claude's context window forgets. Maxim carries architecture, decisions, skill gaps, and handoff state across sessions. Thirteen drift checks run on every session start: docs vs code, counts vs reality, moat claims vs the ledger. Silent regressions surface before they ship, not after.
Read the ADR: Zeigarnik Effect + ADR-002 Executable Contracts →This section was composed through Maxim's own behavioral intelligence skills. Every block names the framework it applied. A tool that claims behavioral rigor should demonstrate it visibly.
Claude Code sessions run many plugins side-by-side: autocomplete, testing, doc generators, MCP servers. Every output flows to the same operator, but only Maxim ships the behavioral-science layer, the fourteen compliance frameworks, and the confidence-tagging rubric. The Maxim Overlay Engine applies those layers to every plugin in the environment, not only Maxim's own skills.
Every installed plugin is enumerated on session start. Maxim inspects each plugin's capabilities and pre-computes a framework pairing per capability. Cached for the session; rebuilt when plugins change.
When a third-party capability is invoked, Maxim injects a short directive naming the matched behavioral framework, the project's active compliance frameworks, and the confidence-tag requirement. Visible. Loggable. Never silently rewrites operator intent.
The project's declared compliance frameworks are applied as review checklists. Work that touches PII, PHI or PCI is routed to security review and flagged when a required control is missing, and the review is written to the audit trail.
Every output above a size threshold is scored by the behavioral audit engine. A confidence tag (🟢 HIGH / 🟡 MEDIUM / 🔴 LOW) appears as a sidebar signal. Every event writes to a local log you can read. Proactive Watch feeds the event into drift-class 13.
config/overlay-profile.yml. Global disable by removing Maxim. No lock-in.Founder, iSystematic Inc. · Maintainer, Maxim
Maxim is built by Nabeel Khan through iSystematic Inc. (Canada). I've spent the last decade building governed AI systems for regulated industries and operator tooling for solo founders: the two audiences Maxim is built for. Maxim is the product I wanted for my own work and couldn't buy: a Claude Code plugin that applies behavioral science to every output, tags confidence honestly, and treats documentation as an Executable Contract.
Maxim's positioning claims are not marketing copy. Each one is governed by a public Architecture Decision Record that names the mechanism, the anti-pattern, and the conditions under which the claim would be retired.
Four more ADRs covering internal architecture (dispatch baseline, Worker license infrastructure, IP-protection layering, external-content boundary) remain confidential. Enterprise buyers with a legitimate audit need can request access via the contact page.
90-day Pro Trial auto-activates on install. Keep using Starter after, or commit to Solo at $19.99.