latest#107
Merged
connerohnesorge merged 1 commit intomainfrom Nov 20, 2025
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request introduces a new agent architecture for implementation, testing, and human escalation, and adds guidance for agent usage and OpenSpec integration. The changes define clear roles and protocols for the
coder,tester, andstuckagents, ensure strict escalation to human input on any failure, and add instructions for using OpenSpec specifications. These improvements are aimed at making the agent workflow robust, reliable, and transparent, especially around error handling and visual testing.Agent Definitions and Protocols
.claude/agents/coder.mdto define thecoderagent as a specialist for implementing specific tasks, with strict rules for error escalation and completion reporting..claude/agents/tester.mdto define thetesteragent as a Playwright MCP visual QA specialist, with detailed workflow and mandatory escalation on any visual/test failure..claude/agents/stuck.mdto define thestuckagent as the emergency escalation point for all errors, failures, or uncertainties, with strict rules for obtaining human input and relaying actionable guidance.Agent Usage and OpenSpec Integration
AGENTS.mdwith instructions for when and how agents should refer to OpenSpec for planning, proposals, and architecture changes, ensuring agents use authoritative specs before coding.These changes establish a clear, reliable agent workflow, enforce rigorous error handling and human escalation, and improve documentation and integration with project specifications.