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/mocaos/cortex-app/verifynpx skills add mocaOS/cortex-app --skill verifygit clone --depth 1 https://github.com/mocaOS/cortex-appWhat 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 | $0.00026 | $0.00628 |
| Opus 5 | $0.00013 | $0.00314 |
| Sonnet 5 | $0.00005 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade C, and why
verify scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- Direct API: `KEY=$(docker exec cortex-backend printenv ADMIN_API_KEY)` then Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -H "X-API-Key: $KEY" http://localhost:8000/api/...`. How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verifying Cortex changes in the running app
The dev stack runs in Docker with hot-reloaded mounted source — no rebuild needed for frontend/backend edits:
cortex-frontend→ http://localhost:3000 (Next.js dev)cortex-backend→ http://localhost:8000 (FastAPI)cortex-neo4j→ 7474/7687
Auth
- UI login: real form at
/login; credentials from container env:docker exec cortex-frontend printenv ADMIN_EMAIL(andADMIN_PASSWORD). Login sets asessioncookie ANDadmin_api_keyin localStorage (the frontend sends it asX-API-Keyon fetches). - Direct API:
KEY=$(docker exec cortex-backend printenv ADMIN_API_KEY)thencurl -H "X-API-Key: $KEY" http://localhost:8000/api/....
Browser driving (Playwright)
Local node (nvm v23) works; browsers cache under ~/.cache/ms-playwright.
mkdir -p /tmp/verify-x && cd /tmp/verify-x
npm init -y && npm install playwright
npx playwright install chromium # if cached revision mismatches
ADMIN_EMAIL=$(docker exec cortex-frontend printenv ADMIN_EMAIL) \
ADMIN_PASSWORD=$(docker exec cortex-frontend printenv ADMIN_PASSWORD) \
node script.mjs
Login flow in a script: goto /login, fill input[name="email"] /
input[name="password"], click button[type="submit"], wait for URL to
leave /login. Then navigate anywhere (e.g. /documents).
- Document cards on
/documents: locate viadiv.glasscontainingh4[title*="<filename>"]; action buttons carrytitleattributes ("Download document", "View document", …). - To assert download-vs-tab behavior: listen for the page
downloadevent and the contextpageevent (popup).
Test data
- Upload a throwaway doc without triggering processing:
curl -H "X-API-Key: $KEY" -F "[email protected]" http://localhost:8000/api/upload(stayspendinguntil/api/documents/process-pendingis called). - Clean up:
curl -X DELETE -H "X-API-Key: $KEY" http://localhost:8000/api/documents/<id>.
Gotchas
- Frontend typecheck must run in the container (
docker exec cortex-frontend npx tsc --noEmit) — localnode_modulesis incomplete/root-owned. - Don't kick off document processing on real PDFs — it triggers LLM extraction (cost + long-running).
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 · 60 lines · 26 tokens per session scan C 37fe6649253a
verify is a skill published in the GitHub repository mocaOS/cortex-app (5 stars, last pushed 14d ago), licensed Apache-2.0. It adds 26 tokens to every session and 628 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (harvests environment variables, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
memclaw
The agent's persistent long-term memory — the only knowledge that survives across sessions, shared across the fleet under access control. Consult it at the start of a task to recall prior decisions, findings, and rules before acting, and write outcomes, decisions, and lessons as work completes. Use whenever a caura…
company-brain
How an agent should operate as one mind inside a shared Company Brain built on Caura — recall before acting, obey fleet keystones, reuse and publish skills, and report outcomes so every task compounds across the whole organization. Use this whenever you work as part of a Caura-connected team or fleet and your work…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
plan
Plan mode: write markdown plan, no execution.