GitHub - jaksa76/agentize · GitHub
/" data-turbo-transient="true" />
Skip to content
Search or jump to...
Search code, repositories, users, issues, pull requests...
-->
Search
Clear
Search syntax tips
Provide feedback
--><br>We read every piece of feedback, and take your input very seriously.
Include my email address so I can be contacted
Cancel
Submit feedback
Saved searches
Use saved searches to filter your results more quickly
-->
Name
Query
To see all available qualifiers, see our documentation.
Cancel
Create saved search
Sign in
/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up
Appearance settings
Resetting focus
You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
jaksa76
agentize
Public
Notifications<br>You must be signed in to change notification settings
Fork
Star
main
BranchesTags
Go to file
CodeOpen more actions menu
Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit
History<br>42 Commits<br>42 Commits
.claude-plugin
.claude-plugin
.claude/skills
.claude/skills
plugins/agentize
plugins/agentize
ADOPTION.md
ADOPTION.md
LICENSE.md
LICENSE.md
READINESS.md
READINESS.md
README.md
README.md
TODO.md
TODO.md
VISION.md
VISION.md
View all files
Repository files navigation
Agentize
A framework for evaluating and improving AI agent readiness and adoption in software projects. Two complementary maturity models assess structural project properties (Agent Readiness) and how deeply agents are embedded in development workflows (Agent Adoption), with Claude Code skills to assess and raise both dimensions automatically.
Agentic coding amplifies what is already there — Agentize lets teams assess their starting point, understand exactly what is blocking the next level, and implement improvements systematically.
Agent Readiness Maturity Model
Measures structural, environmental, and documentary properties that determine how effectively an AI agent can understand, navigate, modify, and verify the project.
Level<br>Name<br>What it means
Uninstrumented<br>No meaningful context or feedback for an agent.
Foundation<br>Enough structure for small, targeted steps. Human must verify every output.
Guided Autonomy<br>Humans guide at the feature level. Agents can plan, write tests, and navigate architecture.
Supervised Autonomy<br>Humans operate strategically. Agents implement most stories end-to-end autonomously.
Scored across 11 criteria :
ID<br>Criterion<br>Max level
C1.1<br>Codebase Accessibility
C2.1<br>Setup Automation
C3.1<br>Architecture Depth
C4.1<br>Requirements Access
C5.1<br>Runnability
C5.2<br>Unit Test Coverage
C5.3<br>Integration and E2E Coverage
C6.1<br>Static Analysis
C7.1<br>Test Isolation
C8.1<br>CI/CD Automation
C8.2<br>Observability
See READINESS.md for full level definitions and criterion fulfillment tables.
Agent Adoption Maturity Model
Measures how deeply AI agents are embedded in a team's development process.
Level<br>Name<br>What it means
Unassisted<br>Agents play no meaningful role.
Vibe Coding<br>Agents assist with bounded coding tasks, directed step-by-step.
Agentic Engineering<br>Agents plan and implement complete features. Developers review outcomes.
Software Factory<br>Agents continuously pull stories from the backlog with minimal per-story human involvement.
Sustainable Autonomy<br>Agents proactively address tech debt, security, and dependencies without human initiation.
Scored across 8 criteria :
ID<br>Criterion<br>What it measures
A1<br>Agent Context Availability<br>Project-specific guidance available to agents (CLAUDE.md, MCP servers)
A2<br>Agent-Authored Contributions<br>Proportion of changes with significant agent involvement
A3<br>Feedback Loop Closure<br>Degree to which agents verify their own work
A4<br>Task Scope<br>Granularity of work agents handle end-to-end
A5<br>Workflow Integration<br>How embedded agents are in PRs, code review, CI, and deployment
A6<br>Autonomous Operation<br>Whether agents are triggered by events/schedules or always started manually
A7<br>Proactive Quality Management<br>Whether agents improve codebase health on their own initiative
A8<br>Planning Integration<br>Whether agents participate in story generation and backlog grooming
See ADOPTION.md for full level definitions and criterion fulfillment tables.
How to Use
Assess your current level:
/assess-readiness — score all 11 readiness criteria with gaps and recommendations
/assess-adoption — score all 8 adoption criteria with gaps and recommendations
Raise your level (implements all blocking improvements in one step):
/improve-readiness
/improve-adoption
Verify or improve a single criterion:
/verify-c1-1 … /verify-c8-2, /verify-a1 … /verify-a8
/improve-c1-1 … /improve-c8-2, /improve-a1 … /improve-a8
Installation
Via Claude Code plugin marketplace (recommended)
/plugin marketplace add jaksa76/agentize<br>/plugin...