open-supply-hub: Skill for Claude Code

.agent/skills/moderation-email/SKILL.md

moderation-email is a skill for Claude Code, Codex from opensupplyhub/open-supply-hub. It costs 123 tokens per session (2,375 once invoked), scanned A, original, MIT.

A process that turns a moderator's error and duplicate tags in a Google Sheet into a finished contributor feedback email.

In plain words
What is it for?
It is for reading tagged review sheets and producing the email in Markdown and HTML.
Why use it?
It removes the need to manually copy reviewed spreadsheet findings into an email and keeps the message based on the moderator's decisions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is opensupplyhub/open-supply-hub's own configuration. It tells Claude Code and Codex how to work on open-supply-hub 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 open-supply-hub configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 .agent/skills/_shared/parse_processed.py <dump-file> --csv <output_dir>/<id>/tagged.csv.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/opensupplyhub/open-supply-hub/main/.agent/skills/moderation-email/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/opensupplyhub/open-supply-hub

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 moderation-email

README.md
[![agentmods](https://agentmods.dev/badge/skills/opensupplyhub/open-supply-hub/moderation-email/github.svg)](https://agentmods.dev/skills/opensupplyhub/open-supply-hub/moderation-email)
Your own site
<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.

agentmods 80×15 button for moderation-email

Your own site · 80×15
<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>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,375 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00123 $0.02375
Opus 5 $0.00062 $0.01188
Sonnet 5 $0.00025 $0.00475
Haiku 4.5 $0.00012 $0.00237

Measured 8d ago against content hash 0072b92520e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

.agent/skills/moderation-email/SKILL.md · 207 lines

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.
  • python3 on PATH (the two helper scripts are dependency-free).
  • open in 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_metadata on 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_content returns all tabs concatenated (large workbooks arrive as a saved tool-result file — even better). Parse with the skill's parser in ONE call:

Read the full file on GitHub · 207 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. 8d ago First seen · 207 lines · 123 tokens per session scan A 0072b92520e1

Subscribe to this mod's changes

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.

Related

Other skills, from other repositories