cortex-remember-global

A Cortex workflow for saving knowledge that should be available in every project, such as coding conventions, architecture rules, infrastructure facts, security policies, or team agreements. Cortex is a memory system that can recall this shared information across projects.

In plain words
What is it for?
Use it when a rule, fact, or agreement applies broadly rather than to just the current codebase.
Why use it?
It prevents important cross-project knowledge from being stored only in one repository or forgotten between sessions.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/cdeust/cortex/cortex-remember-global
Any agent
npx skills add cdeust/Cortex --skill cortex-remember-global
Clone the repo
git clone --depth 1 https://github.com/cdeust/Cortex

Made for: Claude Code, Codex.

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 913 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00099 $0.00913
Opus 5 $0.00049 $0.00456
Sonnet 5 $0.00020 $0.00183
Haiku 4.5 $0.00010 $0.00091

Measured yesterday against content hash a7235c276e0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

skills/cortex-remember-global/SKILL.md · 85 lines

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

Read the full file on GitHub · 85 lines

Changes

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.

  1. yesterday First seen · 85 lines · 99 tokens per session scan A a7235c276e0e

Subscribe to this mod's changes

cortex-remember-global is a skill published in the GitHub repository cdeust/Cortex (71 stars, last pushed 3d ago), licensed MIT. It adds 99 tokens to every session and 913 once invoked, about $0.0005 per session on Opus 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.

Related

Other skills, from other repositories

food-order

Reorder previous Foodora orders, preview cart contents, and track delivery ETA/status with ordercli. Use when the user wants to reorder food, check delivery status, or browse recent Foodora order history. Never confirm an order without explicit user approval.

Bitterbot-AI/bitterbot-desktop · 53 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

genesis-development

This skill should be used when developing, debugging, refactoring, or building Genesis itself — tasks like "fix this in Genesis", "add a new MCP tool", "wire up the runtime", "Genesis won't start", "create a worktree", "debug the bridge", or "add a capability". Applies to any task modifying files under src/, .claude/…

WingedGuardian/GENesis-AGI · 115 tokens

client-scripts

Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.

serac-labs/serac · 45 tokens

agoragentic-transaction-assurance

Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…

rhein1/agoragentic-integrations · 65 tokens

linkding

Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.

jmagar/claude-homelab · 69 tokens