القائمة
Update AGENTS.md and agent_docs/ following best practices. Use when modifying agent guidelines, adding new documentation, or restructuring agent instructions.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | agents-update |
| description | Update AGENTS.md and agent_docs/ following best practices. Use when modifying agent guidelines, adding new documentation, or restructuring agent instructions. |
Keep AGENTS.md under 140 LOC. Move detailed content to agent_docs/, don't just delete.
AGENTS.md ≤ 140 LOC: Quick reference + links only agent_docs/: Complete instructions with examples
| AGENTS.md Section | Target agent_docs/ File | Status |
|---|---|---|
| Quick Reference | scripts/ | ✓ commands |
| Change Workflow | agent_docs/code_conventions.md | ✓ |
| Core Invariants | agent_docs/code_conventions.md | ✓ |
| Common Pitfalls | agent_docs/code_conventions.md | ✓ |
| Tool Selection | agent_docs/code_conventions.md | ✓ |
| Atomic Change Rules | agent_docs/git_workflow.md | ✓ |
| Required Checks | agent_docs/building_the_project.md | ✓ |
| Git Workflow | agent_docs/git_workflow.md | ✓ |
| Feature Flags | agent_docs/building_the_project.md | ✓ |
| Security | agent_docs/code_conventions.md | ✓ |
| Environment Variables | agent_docs/code_conventions.md | ✓ |
| Performance Targets | agent_docs/code_conventions.md | ✓ |
| Disk Space | agent_docs/building_the_project.md | ✓ |
| Planning & Decisions | plans/ROADMAPS/ROADMAP_ACTIVE.md | ✓ |
goap-agent skill to decomposewc -l AGENTS.md # Must be ≤140
ls agent_docs/ # Verify all files exist
wc -l AGENTS.md ≤ 140See references/AGENTS_UPDATE_REFERENCE.md for detailed workflow.
Checkpoint episodes and create handoff packs for multi-agent session continuity
Configure, test, benchmark, and manage embedding providers for semantic search and vector operations
Create and traverse typed relationships between episodes for dependency tracking and knowledge graphs
Manage episode tags for organization, filtering, and retrieval across the memory system
Generate task playbooks and explain patterns using learned strategies from episodic memory
Record and analyze recommendation sessions and feedback to drive the self-learning loop