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-automatenpx skills add cdeust/Cortex --skill cortex-automategit 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 | $0.00093 | $0.00963 |
| Opus 5 | $0.00046 | $0.00481 |
| Sonnet 5 | $0.00019 | $0.00193 |
| Haiku 4.5 | $0.00009 | $0.00096 |
Grade A, and why
cortex-automate 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automate — Triggers, Rules, and Sync
Keywords
trigger, rule, automate, remind me when, auto-remember, sync instructions, push to CLAUDE.md, prospective memory, keyword trigger, file trigger, domain trigger, time trigger, filter rule, boost rule
Overview
Set up proactive automation in Cortex — triggers that fire when conditions are met (like opening a specific file or entering a domain), rules that filter or boost memories during recall, and syncing top insights back into CLAUDE.md for persistent project instructions.
Use this skill when: You want Cortex to proactively surface information based on context, filter out noise during recall, or keep CLAUDE.md updated with memory-derived insights.
Workflow
Triggers — Proactive Memory Recall
Create triggers that fire automatically when conditions match:
Keyword trigger — fires when a query/context contains specific words:
cortex:create_trigger({
"type": "keyword",
"pattern": "authentication",
"memory_id": <id>,
"message": "Remember: we decided to use JWT with refresh tokens, not sessions"
})
File trigger — fires when a specific file is being worked on:
cortex:create_trigger({
"type": "file",
"pattern": "pg_store.py",
"memory_id": <id>,
"message": "This file has a known issue with connection pooling under load"
})
Domain trigger — fires when entering a specific project domain:
cortex:create_trigger({
"type": "domain",
"pattern": "cortex",
"memory_id": <id>,
"message": "Priority: finish the refactoring plan before adding new features"
})
Time trigger — fires after a time condition:
cortex:create_trigger({
"type": "time",
"pattern": "7d",
"memory_id": <id>,
"message": "It's been a week — run consolidation"
})
Triggers fire up to 5 times by default, then deactivate. They appear in the query_methodology response at session start.
Rules — Filter and Boost During Recall
Add rules that modify recall behavior:
Soft rule (boost/penalize score):
cortex:add_rule({
"type": "soft",
"scope": "domain:cortex",
"condition": "tag:architecture",
"weight": 1.5,
"description": "Boost architecture memories in Cortex domain"
})
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 · 128 lines · 93 tokens per session scan A b843b61928dd
cortex-automate is a skill published in the GitHub repository cdeust/Cortex (71 stars, last pushed 4d ago), licensed MIT. It adds 93 tokens to every session and 963 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.
Other skills, from other repositories
skill-feedback-writer
Use to identify missing instructions in another skill based on its output.
chatgpt-app-builder
Build, modify, debug, migrate, review, or verify TypeScript MCP servers and MCP Apps with mcp-use. Use for tools, resources, prompts, middleware, Views, authentication, Skills over MCP, scaffolding, and advanced features.
moltbook
Participate in Moltbook — the social network for AI agents. Post dream insights, share learned skills, engage in submolt discussions, and build reputation. Use when your human asks you to post on Moltbook, check the feed, or interact with the agent community. Also used during heartbeats for periodic social engagement.
xcodebuildmcp-runtime-boundary-review
Use when reviewing XcodeBuildMCP runtime boundary changes across MCP, direct CLI invocation, daemon-routed tools, and Xcode IDE bridge routing.
utcp-cli
Call external APIs, MCP servers, and CLI tools by writing TypeScript code that runs in a sandbox — without MCP. Use when the user wants the agent to use a tool/API/integration (e.g. "search Open Library", "read my Notion", "call this REST API") in an environment that has a shell but no MCP config and no settable…
protocol-quiet-in-groups
Enforces PROTOCOLS.md "stay quiet in group chats" deterministically. Blocks outbound messages in Discord/Telegram/Slack/etc group channels when the bot was not @mentioned and recently spoke.