ompsure
  • Reviews
  • Pro
  • Pricing
  • Template
Sign InSign Up
ompsure

Code quality that happens automatically.
Free for personal use.

Audience

  • Who's It For?
  • For Creators
  • For Developers

Features

  • Code Graph
  • Security
  • Code Review
  • Testing
  • Deployment
  • Memory

Product

  • Plugins
  • Control Panel
  • Proof
  • Catalog
  • How It Works

Plans

  • Pricing
  • Pro Patterns
  • Commercial License
  • Starter Template

Resources

  • Getting Started
  • Documentation
  • Reviews
  • Affiliate Program

© 2026 Et'al Software Solutions. All rights reserved.

  • Template License
  • Plugin License
  • Refund Policy
  • GitHub
Viewing as
ProofMechanismClassifier
Why

Anyone can write a rulebook. Getting it read is the hard part.

There are two ways to put rules in front of an AI — one it has to choose to read, and one it can't skip. Composure is built on the second.

See the patterns

Choose-to-read vs. can't-skip — documented by the vendors themselves

  1. 1

    Model-elected: Claude Code's Agent Skills load a SKILL.md body only when the model decides the description matches. Anthropic's own skill-authoring guidance names the failure mode directly: "ignored content," "does the Skill activate when expected?"

  2. 2

    Forced injection: Claude Code's CLAUDE.md auto-loads unconditionally; Cursor's "Always"/"Auto Attached" rules work the same way — no decision for the model to get wrong.

  3. 3

    Composure's pattern hints are in the injection category: a native Claude Code hook runs our classifier and writes the classification and any matching pattern hints into the model's context before its turn begins.

What actually happens when you press enter

The matching is plain machinery, not another AI guessing — which is why it works the same way every time. Here's the journey your request takes before your AI even starts:

1The check runs first

The moment you press enter, Composure steps in — before your AI reads anything. Its job is to set the table for the turn, not to clean up after it.

terminal
$you press enter$# before the model reads a word —$# the classifier runs first$# native hook · deterministic · zero tokens

2Your request is understood

Your words are matched against a curated index — the same way every time, no guessing. A "let's plan this" request is recognized as planning; a "is this safe" request as security work. Small talk is recognized too — and left alone.

terminal
$"let's plan the booking flow"$# recognized: planning work$"is this endpoint safe?"$# recognized: security work$"thanks!"$# small talk — nothing injected

3The right rules are picked

If your request touches something the rulebook covers, the best-matching rules are chosen — only the few most relevant, so your AI is guided, not flooded. Rules above your plan show up as "this exists" pointers instead.

terminal
$"add invoicing to my clients app"$# match: Commercial documents$# match: Deals and pipelines$# best few only — never a flood

4Everything arrives before your AI starts

The understanding, the guidance, and the chosen rules are placed in front of your AI before it writes its first word. It never answers your raw request without them.

terminal
$# in context before the first word:$#   what kind of work this is$#   which patterns govern it$#   the guidance for this class$Claude: Following the catalog's shape…

5No repeats

A rule your AI already saw this session isn't sent again — the help gets quieter as the session goes on, not noisier.

terminal
$# later, same session:$"now add invoice PDFs"$# Commercial documents — already$# surfaced · not injected again

what you actually see

terminal
$"add invoicing to my clients app"$# Claude: Following the catalog's shape for this —$#   Commercial documents · Deals and pipelines$# Claude: Invoices, line items, and totals built$#   as one entity set — not a guessed scaffold.
Walk through real asks, step by step

What this page does not claim

This is a comparison of delivery mechanisms, not a claim that AIs are lazy — nothing here says the AI skips reading to save effort. The documented failure is simpler: a rule the AI has to choose to read sometimes doesn't get chosen.

See what corrects it.

The whole rulebook. Delivered without a maybe.

Browse the patternsBack to how it works

Or see what the first 10 minutes look like →