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 commands/get-convex/convex-agent-plugins/deploy-guardgit clone --depth 1 https://github.com/get-convex/convex-agent-pluginsWhat 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 | $0.00029 | $0.00783 |
| Opus 5 | $0.00015 | $0.00392 |
| Sonnet 5 | $0.00006 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
deploy-guard 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 3d 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deployment target guard
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.
Steps
- IDENTIFY before you act: read
CONVEX_DEPLOYMENTin .env.local,convex.json, and whetherCONVEX_DEPLOY_KEYis set; or call the official Convex MCPstatustool. Classify the target: local-anonymous | dev | preview | prod. If two sources disagree, resolve before proceeding. - ANNOUNCE in one line before any deployment-affecting command:
target: dev (joyful-capybara-123, personal dev). Never run the command in the same breath as discovering the target — announce first. - PROD needs a FRESH explicit yes: before
npx convex deploy(when it resolves to prod),npx convex run --prod,env seton prod, snapshotimport/exporton 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. - MCP safety defaults: start the official MCP scoped non-prod (
--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'. - READ-ONLY session mode: when the user says 'read-only' / 'don't change anything', honor it absolutely for the rest of the session — no deploy, no env set/remove, no mutations via
run, no imports; start the MCP with--disable-tools run,envSet,envRemove. - Wrong-deployment diagnosis: when a deploy 'didn't change anything', do NOT re-deploy harder. Re-run step 1 — the deploy almost certainly landed on a different deployment than the one being observed.
- Ambiguity = stop: if you cannot determine which deployment a command will hit, find out (status tool; compare
npx convex env listfingerprints) — never guess.
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.
- 3d ago First seen · 25 lines · 29 tokens per session scan A d10123fafaf4
deploy-guard is a command published in the GitHub repository get-convex/convex-agent-plugins (112 stars, last pushed 5d ago), licensed MIT. It adds 29 tokens to every session and 783 once invoked, about $0.0001 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 commands, from other repositories
account
This API allows you to manage your Scaleway Projects.
domains
Apply the CLI runtime and safety contract before executing a command. Runtime --help is authoritative.
deploy
Build, test, deploy with staged rollout.
d1-migration
Run D1 migration workflow — generate, inspect, apply.
deploy
Deploy a frontend (React, Next.js, or static HTML) to a live URL on Butterbase.
deploy
Build a container image, push it, and deploy the service to the Akka platform. This is the transition from local development to development on the AAO platform.