Save explicitly supplied durable knowledge as a review candidate in Global Agent Memory after duplicate detection.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add ozankasikci/global-agent-memory --skill gam-remember --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Gam Remember?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ozankasikci-gam-remember)More formats (shields.io, HTML) on the badges page.
---
name: gam-remember
description: Save explicitly supplied durable knowledge as a review candidate in Global Agent Memory after duplicate detection.
disable-model-invocation: true
allow_implicit_invocation: false
---
# GAM Remember
Treat text supplied with this invocation as the knowledge the user explicitly wants remembered. If it is empty or ambiguous, ask what should be remembered.
1. Never store credentials, tokens, secrets, raw prompts, or transient logs.
2. Search for duplicates in the current project with `memory_search` before creating anything.
3. If an existing active memory already covers the knowledge, report it instead of creating a duplicate.
4. Otherwise call `memory_remember` with a unique `request_id`, the current `working_directory`, the narrowest correct scope, and one allowed V1 type: `project`, `decision`, `fact`, `solution`, `preference`, `convention`, `session_summary`, `entity`, or `reference`.
5. Create a candidate only. Report its ID and Vault-relative path and tell the user it is awaiting review.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...