Borrowing it
Nothing to install: this file belongs to HomenShum/NodeBenchAI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HomenShum/NodeBenchAI/main/.claude/skills/dep-convex-agent/SKILL.mdgit clone --depth 1 https://github.com/HomenShum/NodeBenchAIWrote 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.
[](https://agentmods.dev/skills/homenshum/nodebenchai/dep-convex-agent)<a href="https://agentmods.dev/skills/homenshum/nodebenchai/dep-convex-agent"><img src="https://agentmods.dev/badge/skills/homenshum/nodebenchai/dep-convex-agent/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.
<a href="https://agentmods.dev/skills/homenshum/nodebenchai/dep-convex-agent"><img src="https://agentmods.dev/badge/skills/homenshum/nodebenchai/dep-convex-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 99 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 100 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 121 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 122 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 101 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 123 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 126 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.01782 |
| Opus 5.5 | $0.00029 | $0.00713 |
| Sonnet 5.5 | $0.00014 | $0.00356 |
| Haiku 4.5 | $0.00007 | $0.00178 |
Grade A, and why
dep-convex-agent 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 1mo 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@convex-dev/agent migration runbook
Last verified
- Working pin:
0.2.10(held since 2026-04-26) - Last attempted upgrade:
0.6.1(reverted same day in PR #150 — produced 422 typecheck errors)
Why we're pinned
@convex-dev/agent 0.6 is a coordinated v0.5 → v0.6 release that piggybacks on the AI SDK v5 → v6 major. It renames two property names on every tool definition (args → inputSchema, handler → execute) and changes the execute function signature from (ctx, args) to (ctx, input, options). We have ~12 files in convex/domains/agents/ that need the rewrite, plus coupled bumps to the entire AI SDK provider family.
When the convex-runtime group bumped this in PR #107 (admin-merged without CI), it silently broke main with 422 typecheck errors. Reverted in PR #150.
Coupled bumps (do all together or not at all)
"@convex-dev/agent": "^0.6.1",
"ai": "^6.0.35", // AI SDK core, currently ^5.0.71
"@ai-sdk/openai": "^3.0.10", // currently 1.x or 2.x
"@ai-sdk/anthropic": "^3.0.13",
"@ai-sdk/groq": "^3.0.8",
"@ai-sdk/google": "^3.0.8",
"@openrouter/ai-sdk-provider": "^2.0.0"
Other @convex-dev/* packages from PR #107 are independent of agent and may move separately:
@convex-dev/auth0.0.80 → 0.0.91 (small, may be safe)@convex-dev/persistent-text-streaming0.2 → 0.3@convex-dev/polar0.6 → 0.9@convex-dev/presence0.1 → 0.3 (component-API break)@convex-dev/rag0.5 → 0.7@convex-dev/twilio0.1 → 0.2@convex-dev/workflow0.2 → 0.3 (component-API break)@convex-dev/workpool0.2 → 0.4 (component-API break)
Recipe (when ready to migrate to v0.6)
Step 1 — Stage the bumps as one commit
npm install \
@convex-dev/agent@^0.6.1 \
ai@^6.0.35 \
@ai-sdk/openai@^3.0.10 \
@ai-sdk/anthropic@^3.0.13 \
@ai-sdk/groq@^3.0.8 \
@ai-sdk/google@^3.0.8 \
@openrouter/ai-sdk-provider@^2.0.0
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.
- 1mo ago First seen · 146 lines · 72 tokens per session scan A f52cd2a88c99
dep-convex-agent is a skill published in the GitHub repository HomenShum/NodeBenchAI (15 stars, last pushed 3d ago), licensed MIT. It adds 72 tokens to every session and 1,782 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
convex-agents
Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration.
convex-agents
Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
create-tech-design
Only use when the user explicitly invokes this skill by name.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…