agentmods.dev

pulse8-ai-cortex-knowledge-vault: Skill for Cursor

.cursor/skills/cortex-deploy/SKILL.md

cortex-deploy is a skill for Cursor from synpulse8-opensource/pulse8-ai-cortex-knowledge-vault. It costs 43 tokens per session (480 once invoked), scanned A, original, Apache-2.0.

A deployment skill for running Cortex with Docker Compose and configuring its environment variables. It also covers syncing files to an EC2 server, restarting containers, and reading service logs.

In plain words
What is it for?
Use it to generate or check environment settings, start Cortex with Docker Compose, verify health, deploy vault files to EC2, restart the service, inspect logs, or configure bulk-ingest mounts.
Why use it?
It gathers the setup and troubleshooting details needed to run Cortex locally or on a server. It helps avoid configuration mistakes involving ports, mounted directories, credentials, and container paths.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is synpulse8-opensource/pulse8-ai-cortex-knowledge-vault's own configuration. It tells Cursor how to work on pulse8-ai-cortex-knowledge-vault itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pulse8-ai-cortex-knowledge-vault configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/env_check.sh # interactive .env generation.

not rated 15repo 3mo ago A scan 43 tokens original Apache-2.0
View source ↗ synpulse8-opensource/pulse8-ai-cortex-knowledge-vault synpulse8.com
Reuse

Borrowing it

Nothing to install: this file belongs to synpulse8-opensource/pulse8-ai-cortex-knowledge-vault. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/main/.cursor/skills/cortex-deploy/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault

Made for: Cursor.

Wrote 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.

agentmods badge for cortex-deploy

README.md
[![agentmods](https://agentmods.dev/badge/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-deploy/github.svg)](https://agentmods.dev/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-deploy)
Your own site
<a href="https://agentmods.dev/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-deploy"><img src="https://agentmods.dev/badge/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-deploy/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.

agentmods 80×15 button for cortex-deploy

Your own site · 80×15
<a href="https://agentmods.dev/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-deploy"><img src="https://agentmods.dev/badge/skills/synpulse8-opensource/pulse8-ai-cortex-knowledge-vault/cortex-deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 480 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00043 $0.00480
Opus 5.5 $0.00017 $0.00192
Sonnet 5.5 $0.00009 $0.00096
Haiku 4.5 $0.00004 $0.00048

Measured 2mo ago against content hash 67021bc7c8b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cortex-deploy scanned grade A with 1 finding 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 2mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:8420/api/v1/health
.cursor/skills/cortex-deploy/SKILL.md · 67 lines

What it actually says

Cortex deploy

Quick start

./scripts/env_check.sh    # interactive .env generation
docker compose up -d
curl http://localhost:8420/api/v1/health

Docker Compose (docker-compose.yml)

Service Port Notes
cortex 8420 API + MCP HTTP
volumes vault, optional /ingest CORTEX_VAULT_PATH, bulk source dir

Env mapping uses CORTEX_ prefix in compose (e.g. CORTEX_TEAMS_WEBHOOK_URL, CORTEX_API_KEY).

Environment dual naming

Settings accept either:

  • VAULT_PATH or CORTEX_VAULT_PATH
  • API_KEY or CORTEX_API_KEY
  • TEAMS_WEBHOOK_URL or CORTEX_TEAMS_WEBHOOK_URL

scripts/env_check.sh writes unprefixed names; compose often maps to CORTEX_*.

Production sync (example)

rsync -avz -e "ssh -i ~/.ssh/key" ./vault/ user@host:~/vault/
ssh user@host 'cd app && docker compose restart cortex'

Host paths in bulk-ingest must exist inside the container (mount at /ingest).

Logs

docker logs cortex 2>&1 | tail -100
# Access lines → stdout (uvicorn.access)
# App logs → stderr (cortex.*)

Health checks

  • GET /api/v1/health
  • Graph: GET /api/v1/graph/stats (with auth if enabled)

Teams notifications

Optional TEAMS_WEBHOOK_URL + TEAMS_APP_BASE_URL for feedback cards (cortex/notify/teams.py). Validated in env_check.sh.

  • Auth: cortex-auth
  • Compiler bulk paths: cortex-compiler
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. 2mo ago First seen · 67 lines · 43 tokens per session scan A 67021bc7c8b1

Subscribe to this mod's changes

cortex-deploy is a skill published in the GitHub repository synpulse8-opensource/pulse8-ai-cortex-knowledge-vault (15 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 480 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

CloudContainersDevOps and cloudai-agentsdockerfastapikarpathy-inspiredkarpathy-llm-wikiknowledge-base
Related

cortex-deploy compared with skills from other repositories

cortex-deploy next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cortex-deploysynpulse8-opensource/pulse8-ai-cortex-knowledge-vaultSkill153mo agoApache-2.0A43Cursor
ecspressokayac/ecspressoSkill1.1kyesterdayMITA17Claude Code
k8s-dev-deploykurtosis-tech/kurtosisSkill5584d agoApache-2.0A78Claude Code, Codex
04-securityskillmds/skillmdSkill1893d agoMITA36Claude Code
infra-conventionsfpindej/netrockSkill2354d agoMITA20Claude Code
coolifyericrisco/rsc-harnessSkill5032d agoMITB100Claude Code, Codex
isrvd-opsrehiy/isrvdSkill25todayApache-2.0A96Claude Code, Codex