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/moderation-email/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/moderation-email)<a href="https://agentmods.dev/skills/opensupplyhub/open-supply-hub/moderation-email"><img src="https://agentmods.dev/badge/skills/opensupplyhub/open-supply-hub/moderation-email/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/moderation-email"><img src="https://agentmods.dev/badge/skills/opensupplyhub/open-supply-hub/moderation-email.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00123 | $0.02375 |
| Opus 5 | $0.00062 | $0.01188 |
| Sonnet 5 | $0.00025 | $0.00475 |
| Haiku 4.5 | $0.00012 | $0.00237 |
Grade A, and why
moderation-email 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 8d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Moderation Email (from the moderator's tags)
Input: a Google Sheets link to the tagged tab of a ~PROCESSED list
report. Output: the finished contributor email (email.md + email.html)
in <output_dir>/<list-id>/.
Prerequisites
- Google Drive access from your agent (the claude.ai Google Drive
integration or equivalent) — steps below use
get_file_metadata/read_file_content/ Drive search. No Drive access? Download the tagged sheet as CSV yourself and give the skill the local file path; everything from parsing onward works the same. python3on PATH (the two helper scripts are dependency-free).openin step 5 is macOS; use your platform's equivalent (xdg-open,start) elsewhere.
0. Load the moderator config — required
Read ~/.config/os-hub/moderation-email.json. If it is missing or
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 of them are stored in this skill.
Config keys used below: docs.templates_doc_id, docs.rules_doc_id,
docs.taxonomy_sheet_id (+ gid), docs.contribot_drive_folder_id,
platform.base_url, platform.monday_board_url,
policy.reject_heuristic_pct (nullable),
policy.reject_heuristic_count (nullable),
policy.second_rejection_cc, output_dir.
1. Read the tagged sheet
get_file_metadataon the file id first: the title (<id>.~PROCESSED.<file-name>) gives the list id.- List display name: newer reports carry a metadata block at the top
of the Summary sheet (list id / list name / contributor / upload date)
— use it. Older reports don't; then ask the moderator (it's on their
Monday item). If still unknown at generation time, write the
placeholder as
==[ADD LIST NAME]==— the renderer turns==...==into a bold yellow highlight that survives the paste into Gmail — and say so in the report. - A bare list id instead of a link → search Drive for
title contains '<id>.~PROCESSED'. read_file_contentreturns all tabs concatenated (large workbooks arrive as a saved tool-result file — even better). Parse with the skill's parser in ONE call:
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.
- 8d ago First seen · 207 lines · 123 tokens per session scan A 0072b92520e1
moderation-email is a skill published in the GitHub repository opensupplyhub/open-supply-hub (21 stars, last pushed today), licensed MIT. It adds 123 tokens to every session and 2,375 once invoked, about $0.0006 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.