Menu
Auto-update .AGENTS.md files based on code changes.
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 | skill-update-memory |
| description | Auto-update .AGENTS.md files based on code changes. |
| tier | 2 |
| version | 1.1 |
Prevent "Agent Amnesia" by keeping .AGENTS.md context files synchronized with code changes.
04-update-docs workflow.Tool: scripts/suggest_updates.py
Usage:
python3 .agent/skills/skill-update-memory/scripts/suggest_updates.py
Bootstrap Migration Mode (optional):
python3 .agent/skills/skill-update-memory/scripts/suggest_updates.py --mode bootstrap --create-missing --development-root src
Output:
.AGENTS.md (or suggested per-directory target in source folders)..AGENTS.md files without overwriting existing ones.--development-root, default: src)./.agent/skills/* and /.cursor/skills/* are always excluded from memory target creation.[!NOTE]
.AGENTS.mdremains optional. If it does not exist, the helper must not fail.
.AGENTS.md Update)For each file listed by the script:
(Deleted).[!IMPORTANT] NEVER delete sections marked
[Human Knowledge]or<!-- PRESERVE -->.
Append new information below manual annotations.
### [new_service.py]
**Purpose:** Handles user authentication.
**Classes:**
- `AuthService` — Main entry point.
- `login()` — Validates credentials.
.AGENTS.md skeletons in source folders.Use when decomposing tasks into parallel sub-tasks or spawning sub-agents. Vendor-agnostic core; load a per-vendor reference for concrete tool names, directory conventions, and invocation syntax.
Use when performing Verification-Driven Development with adversarial approach. Actively challenge assumptions and find weak spots.
Use when performing VDD adversarial review with an opt-in sarcastic, provocative delivery style — a stylistic skin over vdd-adversarial mechanics (exhaustive reporting + objective bar).
Performance critic in adversarial style (optional sarcastic skin). Part of VDD Multi-Adversarial pipeline.
Use when performing OWASP security critique in adversarial style (optional sarcastic skin). Part of VDD Multi-Adversarial pipeline.
Use when performing security vulnerability assessment (OWASP, secrets, dependencies, IaC, LLM, API, MCP/agentic) or when "thinking like a hacker" to find exploits.