Helps prevent changes to the wrong Convex environment by identifying and announcing the target before each operation. Requires fresh consent for production actions and enforces a session-wide read-only mode when requested.
Classify + announce the target Convex deployment before any deployment-affecting command; fresh explicit consent for prod actions; session read-only mode.
Review the instructions the agent will receive before you install.
Deployments are not interchangeable, and most incidents start with a command aimed at the wrong one. Every Convex project has several (personal dev, preview, prod — often across multiple projects on one machine). This guard is the standing discipline: identify, announce, then act — and treat prod as consent-gated, per action, per session.
CONVEX_DEPLOYMENT in .env.local, convex.json, and whether CONVEX_DEPLOY_KEY is set; or call the official Convex MCP status tool. Classify the target: local-anonymous | dev | preview | prod. If two sources disagree, resolve before proceeding.target: dev (joyful-capybara-123, personal dev). Never run the command in the same breath as discovering the target — announce first.npx convex deploy (when it resolves to prod), npx convex run --prod, env set on prod, snapshot import/export on prod, or starting the MCP with prod access — state exactly what will change on which deployment and get an explicit yes in THIS session. A yes given earlier, or for a different target, does not carry.--deployment dev). The two prod flags are DIFFERENT risk levels — keep them split: a read-only prod audit (advisor/insights reading data/logs/insights) passes ONLY --cautiously-allow-production-pii (read tools); --dangerously-enable-production-deployments (which enables MUTATING prod tools) stays OFF unless the user explicitly asked to CHANGE prod this session. Never pair them by default — 'look at prod' must not silently grant 'mutate prod'.run, no imports; start the MCP with --disable-tools run,envSet,envRemove.npx convex env list fingerprints) — never guess.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Review code using shared OpenClaw instructions and a Python helper, while also following the target repository’s review requirements. This skill points to a common installation that supplies the actual review procedure.
Create and manage Axiom alert rules and notification destinations through its API. Connect alerts to email, Slack, or webhooks, check monitor history, and adjust thresholds and evaluation schedules to address excessive or missing alerts.
Investigate production incidents and bugs using logs, metrics, and code evidence. The skill guides hypothesis testing, root cause analysis, fix validation, and reusable investigation notes, with access to configured observability tools such as Axiom.
Design and build Axiom dashboards from logs or metrics, the numerical measurements of system behavior. Create charts, filters, and layouts for monitoring and reporting, or migrate existing Splunk and Grafana panels while validating queries against available data.
Drafts, previews, sends, and records emails for existing ClawHub content rights cases. It supports publisher removal notices and requester updates, requires approval of the final draft, and preserves the exact correspondence in the case record.
Apply ClawHub-specific rules when developing with Convex, including deployment targeting, runtime checks, data migrations, search performance, and skill statistics. It also directs specialized work to the appropriate companion skills.