convex-verify — Claude Code skill: what it does, how to install
convex-verify tests a Convex feature with seeded data, multiple mocked identities, and negative authorization checks. Use it for a specific feature you have built or changed.
npx skills add convex/agent-skills --skill convex-verify -a claude-codeWhat convex-verify does
convex-verify checks an exported Convex query, mutation, or action against its intended behavior. It seeds data, drives the feature as the owner, another authenticated user, and an unauthenticated caller, then asserts both allowed and refused calls. List queries also need a data-scope check so one user cannot receive another user’s rows.
The workflow runs in-process with convex-test, so it does not require a deployment. The setup needs convex-test, vitest, @edge-runtime/vm, and a vitest.config.ts using the edge-runtime environment with convex-test inlined. Run the suite with npx vitest run. A failed negative assertion is treated as an authorization defect; the skill emits a finding with class authz/correctness and the failing probe call.
This skill targets a specific feature rather than a general test framework setup. Check the Vitest configuration first: without the required environment, convexTest(schema) fails with import.meta.glob is not a function. Existing test setup should be reused and composed with the test capability.
What it helps with
- verify a Convex query with seeded rows
- refuse a mutation from the wrong user
- catch cross-user data leaks
- test an unauthenticated caller
- report a failed authorization probe
Example prompts for the agent
- Verify
api.x.cancelas the owner, another user, and an unauthenticated caller; keep the negative assertions. - Seed rows for two users through
convex-test, check the data scope, and runnpx vitest run. - Test this specific Convex feature and emit an
authz/correctnessfinding for every failed assertion.
How to install convex-verify
1Skills CLI (Vercel)
npx skills add convex/agent-skills --skill convex-verify -a claude-code2Manually: put the files in place
~/.claude/skills/convex-verify/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/convex-verify/
1Skills CLI (Vercel)
npx skills add convex/agent-skills --skill convex-verify -a codex2Manually: put the files in place
.agents/skills/convex-verify/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add convex/agent-skills --skill convex-verify -a cursor2Manually: put the files in place
.cursor/skills/convex-verify/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install convex/agent-skills convex-verify2Manually: put the files in place
.github/skills/convex-verify/SKILL.md1Skills CLI (Vercel)
npx skills add convex/agent-skills --skill convex-verify -a gemini-cli2Platform CLI
gemini skills install https://github.com/convex/agent-skills --path skills/convex-verifyManually: put the files in place
.devin/skills/convex-verify/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add convex/agent-skills --skill convex-verify -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about convex-verify
How do I install convex-verify in Claude Code?
Run npx skills add convex/agent-skills --skill convex-verify -a claude-code, then run npx skills add convex/agent-skills --skill convex-verify -a claude-code again. The skill file is at ~/.claude/skills/convex-verify/SKILL.md.
What does convex-verify do?
It tests Convex queries, mutations, and actions with convex-test, using seeded data and several identities. The checks cover successful behavior, refused calls, and whether a query exposes another user’s rows.
What does convex-verify need to run?
It needs convex-test, vitest, @edge-runtime/vm, and a vitest.config.ts with test.environment: "edge-runtime" plus server.deps.inline: ["convex-test"]. Run the tests with npx vitest run.
Source text
SKILL.md · Apache-2.0
---
name: convex-verify
description: "Prove a Convex feature works — seed, drive as multiple mocked users via convex-test, assert behavior including the negative authz cases (wrong user refused, data-scope enforced)."
---
<!-- GENERATED from convex-agents content/capabilities/convex-verify.json — do not edit by hand. -->
# Prove a feature works — seed, drive, assert
A green typecheck proves the code parses; it does not prove a non-owner is actually denied, that a query returns the right rows, or that a mutation has the effect it claims. This capability closes that gap with the loop the whole field is missing: seed → drive → assert, run in-process with `convex-test` so it needs no deployment. Its highest-value assertions are the NEGATIVE ones — the caller who should be refused — because those are exactly the authz defects the 30-app corpus shows are the #1 real bug and the ones a happy-path demo never catches.
## Workflow
1. IDENTIFY the feature to prove: the specific exported query/mutation/action (or a small set) the user just built/changed, and its intended behavior — who should be allowed, what data should come back, what a mutation should change. If the intent is unstated, ask one focused question rather than guessing the contract.
2. SET UP `convex-test`: ensure `convex-test` + `vitest` are dev deps AND a `vitest.config.ts` sets `test.environment: "edge-runtime"` with `server.deps.inline: ["convex-test"]` — WITHOUT that config, `convexTest(schema)` fails at runtime with `import.meta.glob is not a function` (verified). Also install `@edge-runtime/vm`. Then `convexTest(schema)` gives a `t` handle. Reuse the project's existing test setup if present (compose with the `test` capability, don't fork it).
3. SEED realistic data through the app's OWN functions where possible (so the seed exercises the same validators/mutations a real user would), falling back to `t.run(async (ctx) => ctx.db.insert(...))` for fixtures the public API can't create. Seed at least: the caller's own rows AND a second user's rows, so cross-user access is testable.
4. DRIVE the feature as DIFFERENT identities with `t.withIdentity({ subject, tokenIdentifier, ... })`: call the function as (a) the legitimate owner, (b) a different authenticated user, and (c) unauthenticated (`t` with no identity). Use the real identity shape the app's auth uses (subject/tokenIdentifier), matching how ownership is resolved.
5. ASSERT behavior — POSITIVE and NEGATIVE:
- positive: the owner gets the expected rows / the mutation made the expected change (`expect(await t.withIdentity(owner).query(api.x.y, args)).toEqual(...)`).
- NEGATIVE (the load-bearing half): a different user calling the same function is REFUSED — `await expect(t.withIdentity(other).mutation(api.x.cancel, {id})).rejects.toThrow(/forbidden|not authorized|403/)` — and an unauthenticated caller is refused where auth is required. A feature is not proven until the wrong caller is shown to be blocked.
- data-scope: a list/query returns ONLY the caller's rows, never the second user's (assert the second user's row is absent).
6. RUN the tests (`npx vitest run`) and report: what was proven (each positive + negative assertion that passed), and — critically — any assertion that FAILED, because a failed negative assertion is a real authz hole found before ship. Emit findings on the bus (specs/finding.schema.json, class authz/correctness, evidence kind probe-result with the exact failing call) for anything that didn't behave.
7. Do NOT weaken a test to make it pass: if the owner-only query returns another user's row, the FIX is in the function (hand to convex-authz), not in the assertion. A test changed until it's green proves nothing.
## Rules
- Prove behavior, not compilation: every verification includes at least one NEGATIVE assertion (a caller who should be refused is refused) — the happy path alone is not proof.
- Drive the feature as multiple identities with t.withIdentity (owner, other user, unauthenticated) using the app's real subject/tokenIdentifier shape.
- Seed both the caller's rows AND a second user's rows so cross-user access and data-scope are actually testable.
- A vitest.config.ts with environment 'edge-runtime' + convex-test inlined is REQUIRED for convex-test to run (import.meta.glob needs it); author it, don't just author the test file.
- Run in-process with convex-test — no deployment needed; compose with the `test` capability's setup rather than forking it.
- Never weaken an assertion to make it pass: a failing negative test is a real defect → hand the fix to convex-authz/convex-expert, don't edit the test until it's green.
- Emit a bus finding for any assertion that failed (authz/correctness, evidence: the failing probe call) so a composite pass or self-heal can pick it up.
- This drives a SPECIFIC built feature; a request to set up a test framework generally is the `test` capability.
© convex · Apache-2.0 · convex/agent-skills