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 agentmods add skills/cdeust/cortex/cortex-recall-globalnpx skills add cdeust/Cortex --skill cortex-recall-globalgit clone --depth 1 https://github.com/cdeust/CortexWhat 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 | $0.00086 | $0.00735 |
| Opus 5 | $0.00043 | $0.00367 |
| Sonnet 5 | $0.00017 | $0.00147 |
| Haiku 4.5 | $0.00009 | $0.00073 |
Grade A, and why
cortex-recall-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 2d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recall Global — Retrieve Cross-Project Knowledge
Keywords
global, convention, standard, rule, infrastructure, policy, all projects, shared, universal, what's our rule, coding standard, architecture rule, team agreement, cross-project, server config, deployment
Overview
Retrieve global memories — knowledge stored as cross-project that's visible regardless of which project you're currently working in. Global memories include architecture rules, coding conventions, infrastructure facts, security policies, and team agreements.
Note: Regular cortex:recall already surfaces global memories automatically. This skill is for when you specifically want to focus on cross-project knowledge.
Workflow
Step 1: Recall Global Knowledge
Query with any domain — global memories appear alongside domain-specific results:
cortex:recall({
"query": "<topic to search for>",
"max_results": 10
})
Global memories are included in results regardless of the current project domain.
Step 2: Filter to Global Only
To see only global cross-project knowledge, use the unified neural graph:
cortex:open_visualization()
Click the Global filter button (pink) to isolate all global memories.
Click the Global filter — global memories appear as pink nodes connected to all project domains.
Step 3: Explore by Category
Common global recall patterns:
Architecture rules:
cortex:recall({ "query": "architecture rules and principles" })
Infrastructure:
cortex:recall({ "query": "server addresses and database connections" })
Coding conventions:
cortex:recall({ "query": "coding standards and naming conventions" })
Security policies:
cortex:recall({ "query": "security policies and credential management" })
Step 4: Navigate Connections
After finding a global memory, explore what it connects to across projects:
cortex:navigate_memory({
"memory_id": <id>,
"depth": 2
})
Global memories link to all domain hubs in the knowledge graph — following connections shows which projects reference similar concepts.
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.
- 2d ago First seen · 97 lines · 86 tokens per session scan A b54e802ab488
cortex-recall-global is a skill published in the GitHub repository cdeust/Cortex (71 stars, last pushed 4d ago), licensed MIT. It adds 86 tokens to every session and 735 once invoked, about $0.0004 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.
Other skills, from other repositories
xcodebuildmcp-structured-output-review
Use when reviewing XcodeBuildMCP structured output schema changes, schema versioning, manifest outputSchema metadata, and JSON fixture compatibility.
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.
deep-audit
Comprehensive adversarial audit of a theory, proof, math/econ paper, codebase, or set of claims — decompose into components, fan out independent skeptics that must return CONCRETE defects, adjudicate every finding with a separate judge, fix all confirmed defects, then re-verify. Use when correctness must be…
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.…
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/…
forecasting
Superforecasting with calibrated reasoning, Brier score tracking, and prediction ledger management.