Borrowing it
Nothing to install: this file belongs to opensupplyhub/open-supply-hub. 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/opensupplyhub/open-supply-hub/main/.agent/skills/list-review/SKILL.mdgit clone --depth 1 https://github.com/opensupplyhub/open-supply-hubWrote 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/opensupplyhub/open-supply-hub/list-review)<a href="https://agentmods.dev/skills/opensupplyhub/open-supply-hub/list-review"><img src="https://agentmods.dev/badge/skills/opensupplyhub/open-supply-hub/list-review/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/opensupplyhub/open-supply-hub/list-review"><img src="https://agentmods.dev/badge/skills/opensupplyhub/open-supply-hub/list-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 66 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00132 | $0.03499 |
| Opus 5 | $0.00066 | $0.01750 |
| Sonnet 5 | $0.00026 | $0.00700 |
| Haiku 4.5 | $0.00013 | $0.00350 |
Grade A, and why
list-review 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 7d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
List Review
You produce three artifacts for one uploaded facility list, in
<output_dir>/<list-id>/, each in BOTH markdown/CSV (the record) and HTML
(the readable view), rendered with the skill's own script:
python3 .agent/skills/_shared/md2html.py <in.md|in.csv> <out.html>
tagged.csv+tagged.html— tagged rows only (rows with a non-emptyerrororduplicate_pair_id), keyed byrnback to the source sheet. Do NOT transcribe untagged rows — on large lists that dominates the runtime for zero information; the full data lives in the source sheet. Review every row; record only the findings.summary.md+summary.html— stats, ratio vs threshold, recommendation, checklistemail.md+email.html— the finished contributor email
Your tags are suggestions, not decisions. The moderator reviews every one and removes the rows on the platform themselves. Say so in the report, and flag anything you were unsure about rather than quietly resolving it.
0. Load the moderator config — required
Read ~/.config/os-hub/moderation-email.json (shared with the
moderation-email skill). If it is missing or still contains placeholder
values, STOP and tell the moderator: copy
.agent/skills/_shared/config.example.json to that path and fill it from
the internal Data Team Resources Confluence page. Do not proceed with defaults — every document
ID, policy value and URL comes from the config; none are stored here.
Config keys used below: docs.templates_doc_id, docs.rules_doc_id,
docs.taxonomy_sheet_id (+ gid), platform.base_url,
platform.monday_board_url, platform.monday_confirm_reject_board_url, policy.reject_heuristic_pct (nullable),
policy.reject_heuristic_count (nullable), policy.second_rejection_cc,
output_dir.
1. Get the data
Accept any of: a local CSV path, a Google Drive link/file id, or a bare list id.
Always establish the list id AND the list display name (the name shown
on <base_url>/lists/<id> and in the Monday item) before generating the
email — the name fills {List Name} and the id names the output folder.
If either isn't derivable from the input, ask the moderator up front, in
the same message as any tab-access fallback question (one round-trip).
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.
- 7d ago First seen · 272 lines · 132 tokens per session scan A 58d3150ed017
list-review is a skill published in the GitHub repository opensupplyhub/open-supply-hub (20 stars, last pushed today), licensed MIT. It adds 132 tokens to every session and 3,499 once invoked, about $0.0007 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 2026-09-04.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…