supex: Skill for Claude Code

.claude/skills/review-vendor/SKILL.md

review-vendor is a skill for Claude Code from darwin/supex. It costs 19 tokens per session (2,288 once invoked), scanned A, original, MIT.

A workflow for fetching new changes from vendored Git submodules and checking how they affect the supex sidecar before updating them. A Git submodule is a repository recorded at a particular commit inside another repository.

In plain words
What is it for?
It helps review upstream changes in the tang, loon, and vcad submodules and decide whether their recorded commits should be advanced.
Why use it?
It helps prevent updating dependencies without checking workspace version requirements and compatibility first.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is darwin/supex's own configuration. It tells Claude Code how to work on supex itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything supex configures →

View source ↗ darwin/supex
Reuse

Borrowing it

Nothing to install: this file belongs to darwin/supex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/darwin/supex/main/.claude/skills/review-vendor/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/darwin/supex

Made for: Claude Code.

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 review-vendor

README.md
[![agentmods](https://agentmods.dev/badge/skills/darwin/supex/review-vendor/github.svg)](https://agentmods.dev/skills/darwin/supex/review-vendor)
Your own site
<a href="https://agentmods.dev/skills/darwin/supex/review-vendor"><img src="https://agentmods.dev/badge/skills/darwin/supex/review-vendor/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 review-vendor

Your own site · 80×15
<a href="https://agentmods.dev/skills/darwin/supex/review-vendor"><img src="https://agentmods.dev/badge/skills/darwin/supex/review-vendor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,288 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00019 $0.02288
Opus 5 $0.00010 $0.01144
Sonnet 5 $0.00004 $0.00458
Haiku 4.5 $0.00002 $0.00229

Measured 2d ago against content hash 725424919ee7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-vendor 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 2d 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/review-vendor/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review new upstream changes in vendored submodules and analyze their impact on the supex sidecar before deciding whether to roll.

All paths below are relative to the supex repo root.

Submodules

All vendored submodules (vcad/vendor/tang, vcad/vendor/loon, vcad/vendor/vcad) track upstream origin/main directly — no fork, no local patches. The sidecar is written against upstream APIs only; if a roll needs a change in a vendored crate, the change goes upstream as a PR, not into a patch branch.

Workspace coupling — why tang must move with vcad

tang is not an independent upstream dependency. It is a sibling crate inside the vcad workspace: vcad path-depends on it (tang = { path = "../tang/crates/tang", version = "0.2" } in vcad's [workspace.dependencies], mirrored in [patch.crates-io]). The minimum tang version is therefore dictated by the pinned vcad commit, not by what supex itself calls.

This means the right question for rolling tang is "does the vcad commit we're pinning require a newer tang?" — NOT "does the supex sidecar use autodiff?". The sidecar is a separate Cargo workspace that cherry-picks only a few vcad-kernel-* crates, so its build can stay green even when tang lags. But rolling vcad forward while leaving tang behind records an internally inconsistent vendored vcad workspace: anything that resolves the full vcad graph (the native app apple/VcadApp via vcad-ffi, cargo check / IDE diagnostics at the vcad root, just clear-rust-caches, vcad CLI/sim, vcad CI) fails dependency resolution. Roll tang in lockstep with vcad to keep that workspace buildable.

phyz is not vendored. Upstream vcad pins it as a git dependency with a fixed rev in [workspace.dependencies], so Cargo fetches the right commit on demand (network required for the full-graph check). Nothing in supex references phyz directly.

Phase 1: Fetch + changelog

Process all submodules in order: tang, loon, vcad.

For each submodule:

Read the full file on GitHub · 163 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. 2d ago First seen · 163 lines · 19 tokens per session scan A 725424919ee7

Subscribe to this mod's changes

review-vendor is a skill published in the GitHub repository darwin/supex (45 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 2,288 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 2026-09-07.

Related

Other skills, from other repositories

github-review-pr

Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for…

feiskyer/claude-code-settings · 90 tokens

merge-queue

Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.

a5c-ai/babysitter · 29 tokens

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements.

a5c-ai/babysitter · 23 tokens

review-open-pull-requests

List and analyze all open pull requests across GitHub repositories. Shows review status, CI/CD check results, age, and reviewers. Use when triaging PRs, checking team velocity, or identifying stale reviews that need attention.

caipe-io/ai-platform-engineering · 52 tokens

github-review-pr

Review GitHub pull requests with evidence-backed, multi-perspective analysis and false-positive filtering. Use when the user asks to review, inspect, or check a GitHub pull request by number or URL. Default to reporting findings locally; publish comments, submit reviews, or approve only when the user explicitly…

feiskyer/codex-settings · 80 tokens

prepare-pr

End-to-end drives working-tree changes to a review-ready pull request — commit, sync base, squash to one commit, open/update the PR — then KEEPS RUNNING IN-SESSION (poll CI + code-review bots in 5-min rounds, up to 10) fixing every legitimate Critical/High finding and build failure until the PR is review-ready (never…

kirodotdev/KiroCrew · 0 tokens