dep-convex-agent

dep-convex-agent is a skill for Claude Code, Codex from HomenShum/NodeBenchAI. It costs 72 tokens per session (1,782 once invoked), scanned A, original, MIT.

A migration runbook for updating the Convex agent library, which helps build AI agents on Convex. It documents the current version pin, the required coordinated AI SDK update, and the code changes needed for the newer release.

In plain words
What is it for?
Use it when planning or performing the Convex agent upgrade, or when investigating the reported “args was removed in v0.6.0” error.
Why use it?
The newer library version changes tool property names and function arguments, and upgrading only part of the dependency set can create many type-checking errors.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/homenshum/nodebenchai/dep-convex-agent
Any agent
npx skills add HomenShum/NodeBenchAI --skill dep-convex-agent
Clone the repo
git clone --depth 1 https://github.com/HomenShum/NodeBenchAI

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for dep-convex-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/homenshum/nodebenchai/dep-convex-agent.svg)](https://agentmods.dev/skills/homenshum/nodebenchai/dep-convex-agent)
Your own site
<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="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,782 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00072 $0.01782
Opus 5 $0.00036 $0.00891
Sonnet 5 $0.00014 $0.00356
Haiku 4.5 $0.00007 $0.00178

Measured 5d ago against content hash f52cd2a88c99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 5d 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.

.claude/skills/dep-convex-agent/SKILL.md · 146 lines

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 (argsinputSchema, handlerexecute) 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/auth 0.0.80 → 0.0.91 (small, may be safe)
  • @convex-dev/persistent-text-streaming 0.2 → 0.3
  • @convex-dev/polar 0.6 → 0.9
  • @convex-dev/presence 0.1 → 0.3 (component-API break)
  • @convex-dev/rag 0.5 → 0.7
  • @convex-dev/twilio 0.1 → 0.2
  • @convex-dev/workflow 0.2 → 0.3 (component-API break)
  • @convex-dev/workpool 0.2 → 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

Read the full file on GitHub · 146 lines

Changes

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.

  1. 5d ago First seen · 146 lines · 72 tokens per session scan A f52cd2a88c99

Subscribe to this mod's changes

dep-convex-agent is a skill published in the GitHub repository HomenShum/NodeBenchAI (14 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 1,782 once invoked, about $0.0004 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.