agent-ops-state
About
This core skill manages the agent's persistent state files (constitution, memory, focus, issues, baseline) using direct file operations. Developers should invoke it at session start, after meaningful steps, and before concluding to ensure consistent state reading and updating. It handles the foundational read/write cycles for the agent's memory and issue-tracking system.
Quick Install
Claude Code
Recommendednpx skills add majiayu000/claude-skill-registry -a claude-code/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/agent-ops-stateCopy and paste this command in Claude Code to install this skill
GitHub Repository
Related Skills
agent-ops-testing
OtherThe agent-ops-testing skill provides structured guidance for designing tests, executing test suites, and analyzing coverage results beyond basic checks. It integrates with the testing workflow during planning, implementation, and review phases, working with or without the `aoc` CLI. Developers should use it when they need to go beyond baseline verification to implement a comprehensive testing strategy.
agent-ops-tasks
OtherThis skill manages the issue lifecycle within a project, allowing developers to create, refine, triage, and export issues without implementing code. It's designed for tasks like clarifying vague ideas, performing bulk operations, and organizing issues into priority files. Use it for project planning and task management, as it strictly handles issue metadata and always requires a manual handoff for any subsequent implementation work.
agent-ops-focus-scan
OtherThis skill analyzes pending issues to determine the next highest-priority work item and updates the focus.md file accordingly. It enforces an issue-first workflow by ensuring all work originates from tracked issues and respects confidence-based batch limits. Use it to automatically align your development session with the most important pending task.
agent-ops-baseline
OtherThis skill creates a baseline file (.agent/baseline.md) to capture current build/lint/test results, then later compares new runs against it to identify newly introduced issues. It's used when establishing a project's current state or investigating regressions. The skill works with or without external CLI tools by using direct file operations and reads commands from your project's constitution.
