convex-improve-convex-plugin

convex-improve-convex-plugin is a skill for Claude Code, Codex from openclaw/clawhub. It costs 34 tokens per session (415 once invoked), scanned C, original, MIT.

A tool that sends a coding session transcript to the Convex team for an AI review of the quickstart system, after the user gives permission. The review looks for unclear instructions, stuck-agent patterns, tooling problems, and successful practices rather than analyzing end-user data.

In plain words
What is it for?
Use it to submit a session for a system-focused post-mortem, then summarize the most serious findings and suggested fixes along with the useful practices it identified.
Why use it?
It turns problems observed during a session into feedback for improving runbooks, skills, bootstrap scripts, and components. The consent step prevents the transcript from being shared without an explicit choice.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions Codex.

Good fit Use it to submit a session for a system-focused post-mortem, then summarize the most serious findings and suggested fixes along with the useful practices it identified.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openclaw/clawhub/convex-improve-convex-plugin
About the project

ClawHub is a public registry where OpenClaw users publish, version, search, and install text-based agent skills and OpenClaw packages. It provides web browsing, a CLI-oriented API, moderation, vector search, and artifact hosting for code plugins, bundle plugins, and experimental whole-agent packages. The catalogue skills and agents are entries that can be discovered or used through this registry.

openclaw/clawhub · 9,407 stars · on GitHub · clawhub.ai

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.

Any agent
npx skills add openclaw/clawhub --skill convex-improve-convex-plugin
Clone the repo
git clone --depth 1 https://github.com/openclaw/clawhub

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 convex-improve-convex-plugin

README.md
[![agentmods](https://agentmods.dev/badge/skills/openclaw/clawhub/convex-improve-convex-plugin/github.svg)](https://agentmods.dev/skills/openclaw/clawhub/convex-improve-convex-plugin)
Your own site
<a href="https://agentmods.dev/skills/openclaw/clawhub/convex-improve-convex-plugin"><img src="https://agentmods.dev/badge/skills/openclaw/clawhub/convex-improve-convex-plugin/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.

agentmods 80×15 button for convex-improve-convex-plugin

Your own site · 80×15
<a href="https://agentmods.dev/skills/openclaw/clawhub/convex-improve-convex-plugin"><img src="https://agentmods.dev/badge/skills/openclaw/clawhub/convex-improve-convex-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 415 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

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 →

  • high Supply Chain · line 14
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
How audits are shown
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 5.1 $0.00034 $0.00415
Opus 5 $0.00017 $0.00208
Sonnet 5 $0.00007 $0.00083
Haiku 4.5 $0.00003 $0.00042

Measured 10d ago against content hash 20bc30272937, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

convex-improve-convex-plugin scanned grade C with 2 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 10d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

1. Run the anteater-served helper: `curl -fsSL "<anteater>/send-transcript" | bash -s -- --idea "<one-line app idea from this session>"`.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. Run the anteater-served helper: `curl -fsSL "<anteater>/send-transcript" | bash -s -- --idea "<one-line app idea from this session>"`.
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/convex-improve-convex-plugin/SKILL.md · 25 lines

What it actually says

improve-convex-plugin

Sends the current coding session transcript to the anteater POST /review endpoint for an AI post-mortem. The review returns structured findings (ambiguous instructions, agent-stuck patterns, tooling failures, wins) targeted at the runbook, bootstrap script, skills, and components — not end-user data. Sharing is opt-in: the anteater-served helper asks once (Always / Just this once / Never) and remembers the choice.

Workflow

  1. Run the anteater-served helper: curl -fsSL "<anteater>/send-transcript" | bash -s -- --idea "<one-line app idea from this session>".
  2. If it prints CONSENT_REQUIRED (exit 4), the user has not chosen yet — ask them to share Always, Just this once, or Never, then re-run appending --consent always|once|never. Do not send until they answer.
  3. Watch for output markers: REVIEW_SOURCE (transcript found), REVIEW_SUBMITTED id=... (accepted), REVIEW_DONE status=done (findings ready).
  4. Summarize the highest-severity findings for the user: title → target → suggestedFix, then wins. Keep the summary about the system, not the user's data.

Rules

  • Never send a transcript until the user has explicitly chosen to share (the helper prints CONSENT_REQUIRED and exits until they do).
  • REVIEW_NO_TRANSCRIPT means no Claude/Codex .jsonl was found — tell the user.
  • Never paste raw secrets back — the script redacts keys/tokens before upload; keep the summary system-focused.
  • This is a system-improvement loop, not end-user feature feedback.
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. 10d ago First seen · 25 lines · 34 tokens per session scan C 20bc30272937

Subscribe to this mod's changes

convex-improve-convex-plugin is a skill published in the GitHub repository openclaw/clawhub (9,407 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 415 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.