Menu
Update agent submodules, refresh GitHub star counts, and regenerate README table
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | update-repo |
| description | Update agent submodules, refresh GitHub star counts, and regenerate README table |
Update the repository's agent data: pull latest submodule commits, refresh star counts from GitHub, and regenerate the README agent table.
/update-repo [agent-name]
agent-name: update only that agent's submodule# Update specific agent
./scripts/manage-submodules.sh update <agent-name>
# Or update all
./scripts/manage-submodules.sh update
For each updated agent, if agents.yaml has an analyzed_commit, compare it with the new submodule HEAD. If different, print:
⚠️ : submodule 从 更新到 ，分析文档和 demo 可能过时。运行
/check-updates <agent>查看详情。
./scripts/update-stars.sh
./scripts/gen-readme.sh
./scripts/manage-submodules.sh status
./scripts/manage-submodules.sh add <agent-name> firstagents.yamlSummarize blast radius, impacted services, and safe next actions.
Run uv, pytest, then lint in a predictable order.
Codex workflow adapter for this repository. Use when working in agent-cracker to translate Claude-style slash workflows into skill usage, remember manual checks that Claude hooks would normally perform, and keep docs/config/progress files in sync.
Systematically analyze an AI agent's source code across 8 core + 4 optional platform dimensions and output structured analysis to docs/<agent>.md
Audit MVP component, platform mechanism, and advanced mechanism coverage for analyzed agents, identifying gaps and suggesting next steps
Create a minimal reproduction demo for a specific mechanism from an analyzed AI agent (coding or platform)