andreaswasita/copilot-agents-dojo
Skill Claude CodeCodex
Detects high-confidence security risks in code.
A behavioral governance framework for GitHub Copilot agents — skills.md and instructions to make AI coding agents think like senior engineers.
This repository also configures its own agents. See what copilot-agents-dojo tells them →
andreaswasita/copilot-agents-dojo
Skill Claude CodeCodex
Detects high-confidence security risks in code.
andreaswasita/copilot-agents-dojo
Skill Claude CodeCodex needs its repo
Captures lessons and promotes recurring patterns.
andreaswasita/copilot-agents-dojo
Skill Claude CodeCodex
Delegates research and parallel work to sub-agents.
andreaswasita/copilot-agents-dojo
Skill Claude CodeCodex
Writes meaningful tests that actually catch bugs.
andreaswasita/copilot-agents-dojo
Skill Claude CodeCodex needs its repo
Enforces parent-link lineage across requirement layers.
andreaswasita/copilot-agents-dojo
Skill Claude CodeCodex needs its repo
Isolates each task in its own git worktree off main.
andreaswasita/copilot-agents-dojo
Skill Claude CodeCodex
Activates the dojo framework at the start of a session.
andreaswasita/copilot-agents-dojo
Skill Claude CodeCodex needs its repo
Proves work with tests, diffs, and logs before sign-off.
andreaswasita/copilot-agents-dojo
Skill Claude CodeCodex
Replace with the capability this skill provides.
andreaswasita/copilot-agents-dojo
Skill Claude CodeCodex
Defines types and boundaries before implementation.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: