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.
curl -O https://raw.githubusercontent.com/darwin/supex/main/.claude/skills/review-vendor/SKILL.mdgit clone --depth 1 https://github.com/darwin/supexWrote 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/darwin/supex/review-vendor)<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.
<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>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 | $0.00019 | $0.02288 |
| Opus 5 | $0.00010 | $0.01144 |
| Sonnet 5 | $0.00004 | $0.00458 |
| Haiku 4.5 | $0.00002 | $0.00229 |
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.
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:
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.
- 2d ago First seen · 163 lines · 19 tokens per session scan A 725424919ee7
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.
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…
merge-queue
Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
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.
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…
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…