agent-sh

agent-sh/agentsys

Skill Claude CodeCodex

Use when appending structured perf investigation notes and evidence.

agent-sh/agentsys

Skill Claude CodeCodex

Use when profiling CPU/memory hot paths, generating flame graphs, or capturing JFR/perf evidence.

agent-sh/agentsys

Skill Claude CodeCodex

Use when generating performance hypotheses backed by git history and code evidence.

agent-sh/agentsys

Skill Claude CodeCodex

Use when running controlled perf experiments to validate hypotheses.

agent-sh/agentsys

Skill Claude CodeCodex

Use when user asks to "run repo intel", "generate repo map", "analyze repo", "query hotspots", "check ownership", or "bus factor". Unified static analysis - git history, AST symbols, project metadata.

agent-sh/agentsys

Skill Claude CodeCodex

Sync documentation with code. Use when user asks to update docs, check docs, fix stale documentation, update changelog, or after code changes.

agent-sh/agentsys

Skill Claude CodeCodex

Use when user asks to "validate delivery", "check readiness", or "verify completion". Runs tests, build, and requirement checks with pass/fail instructions.

agent-sh/agentsys

Instructions file CodexOpenCode

AGENTS.md instructions for agent-sh/agentsys, covering project memory: agentsys, critical rules (priority order), architecture, commands and core workflow.

agent-sh/agentsys

Instructions file

Claude Code instructions for agent-sh/agentsys, covering agentsys, critical rules, model selection, core priorities and dev commands.

agent-sh/agentsys

Skill Claude CodeCodex

Use when preparing releases, validating cross-platform compatibility, or updating installation infrastructure. Meta-skill for maintaining AgentSys's 3-platform architecture.

agent-sh/computer-use-linux

Skill Claude CodeCodex

Linux desktop observation and control via the computer-use-linux MCP server: accessibility trees, screenshots, window targeting, and input synthesis (click, type, scroll). Works with any MCP host.

agent-sh/agnix

Instructions file CodexOpenCode

AGENTS.md instructions for agent-sh/agnix, covering project memory: agnix, project instruction files, critical rules, architecture and crate dependency graph.

agent-sh/agnix

Instructions file

Claude Code instructions for agent-sh/agnix, covering project memory: agnix, project instruction files, critical rules, architecture and crate dependency graph.

agent-sh/agnix

Plugin Claude Code

Lint agent configurations before they break your workflow. 454 rules for Skills, Hooks, MCP, Memory, Plugins.

agent-sh/agnix

Agent

Lint agent configurations using agnix CLI. Invoke agnix skill and return validation results.

agent-sh/agnix

Command

Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP', or mentions 'agent config issues', 'skill validation'.

agent-sh/agnix

Skill Claude CodeCodex

Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 454 rules across 10+ AI tools.

agent-sh/agnix

Agent

Review pull requests.

agent-sh/agnix

Agent

Review pull requests.

agent-sh/agnix

Agent

Review pull requests.

agent-sh/agnix

Agent

Review pull requests.

agent-sh/agnix

Agent

Review pull requests.

agent-sh/agnix

Agent

Review pull requests.

agent-sh/agnix

Instructions file GitHub Copilot

Copilot instructions for agent-sh/agnix, a project described as: The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plugin for all major IDEs included, with autofixes.