jonathanmr22/pact

Programmatic Agent Constraint Toolkit (PACT): Governance infrastructure for AI coding agents. Claude Code plugin marketplace.

27
/ 100
Experimental

PACT helps solo developers and small teams govern their AI coding agents, like Claude Code or Copilot Workspace, by providing infrastructure that prevents common errors. It takes in your coding tasks and project guidelines, and outputs more reliable, higher-quality code by guiding the agent through better decision-making processes. This is for individual developers or small development teams who rely on AI agents for coding and need to ensure consistency and prevent mistakes.

Use this if you are a developer struggling with your AI coding agent making suboptimal decisions, forgetting context, or producing unreliable code, even when given clear instructions.

Not ideal if you are an individual who does not use AI coding agents as part of your development workflow, or if you already have robust governance and memory systems for your agents.

AI-assisted coding software development workflow developer productivity AI agent governance code quality assurance
No Package No Dependents
Maintenance 13 / 25
Adoption 5 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

9

Forks

Language

Shell

License

MIT

Category

coding-agent

Last pushed

Apr 03, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/jonathanmr22/pact"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.