Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add cdeust/Cortex --skill cortex-remember-globalgit clone --depth 1 https://github.com/cdeust/CortexWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cdeust/cortex/cortex-remember-global)<a href="https://agentmods.dev/skills/cdeust/cortex/cortex-remember-global"><img src="https://agentmods.dev/badge/skills/cdeust/cortex/cortex-remember-global/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cdeust/cortex/cortex-remember-global"><img src="https://agentmods.dev/badge/skills/cdeust/cortex/cortex-remember-global.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00099 | $0.00913 |
| Opus 5.5 | $0.00040 | $0.00365 |
| Sonnet 5.5 | $0.00020 | $0.00183 |
| Haiku 4.5 | $0.00010 | $0.00091 |
Grade A, and why
cortex-remember-global scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remember Global — Store Cross-Project Knowledge
Keywords
global, everywhere, all projects, cross-project, shared, universal, convention, standard, rule, infrastructure, policy, team agreement, always, never, architecture rule, coding standard
Overview
Store knowledge that transcends any single project into Cortex's global memory. Global memories bypass domain filtering during recall — they're visible from every project you work on. Use this for architecture rules, coding conventions, infrastructure facts, security policies, and team agreements.
Cortex auto-detects many global patterns (clean architecture, dependency injection, server addresses, etc.), but use this skill explicitly when you want to guarantee cross-project visibility.
Workflow
Step 1: Identify Cross-Project Knowledge
Good candidates for global memory:
- Architecture rules: "Always follow clean architecture — inner layers never import outer layers"
- Coding conventions: "Use UTC timestamps in all database layers"
- Infrastructure: "Production database at db.internal:5432, daily backups at 3AM UTC"
- Security policies: "Rotate API keys every 90 days, store in 1Password vault"
- Team agreements: "PRs must be under 300 lines, always include tests"
- Reusable patterns: "Use factory injection for all handler composition roots"
Not global (project-specific): bug fixes, feature decisions for one project, file-specific notes.
Step 2: Store as Global
cortex:remember({
"content": "<clear, self-contained knowledge that applies across projects>",
"tags": ["<category>", "<topic>"],
"is_global": true,
"force": true
})
Content guidelines:
- Write as a rule or fact, not a narrative: "Always use UTC" not "Today we decided to use UTC in the auth service"
- Include the why when it's a rule: "Use dependency injection because it enables testing and follows SOLID"
- Keep it universal — no project-specific file paths, PR numbers, or branch names
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 85 lines · 99 tokens per session scan A a7235c276e0e
cortex-remember-global is a skill published in the GitHub repository cdeust/Cortex (75 stars, last pushed 2d ago), licensed MIT. It adds 99 tokens to every session and 913 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
xmemo-memory
Persistent, user-owned memory for agents. Use the standalone runtime to remember, recall, search, preserve restart continuity, manage TODOs and expenses, inspect account overview, activity and stats diagnostics, or diagnose XMemo when MCP tools are unavailable. Not for codebase search, web search, or short-lived…
temporal-query
Answer time-travel questions over stored memory — what was believed at a past point in time, when a belief changed, and what replaced it. Use when the user says "as of", "back in", "at the time", "history of", "timeline", "what did I think then", or asks why a current memory contradicts an older one.
knowledge-audit
Review and clean up stored memories — find duplicates, contradictions, stale entries, and consolidate.
memory-commit
Use when the user explicitly says "remember this", "save this", "ghi nho", "luu lai", "save for next time", or otherwise asks to persist the immediately preceding context. Captures with the appropriate contexttype (decision, preference, fact, skill, task, conversation) so future sessions can retrieve it accurately.
recall-context
Use at session start, before significant decisions, or when a new task references a known project to recall mnemo memories matching the current working directory, recently edited files, or topic keywords. Helps maintain continuity across sessions and avoid redoing past research.
passport-bootstrap
Use when the user installs mnemo-mcp on a fresh machine and wants to restore prior memory state from S3 or Google Drive (Phase 2 passport sync). Triggers on phrases like "set up mnemo on this machine", "restore my memory passport", "import passport", "bootstrap mnemo", or when the user says they got a new laptop / VM…