Borrowing it
Nothing to install: this file belongs to alp82/aistack. 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/alp82/aistack/main/.claude/skills/news-draft/SKILL.mdgit clone --depth 1 https://github.com/alp82/aistackWrote 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/alp82/aistack/news-draft)<a href="https://agentmods.dev/skills/alp82/aistack/news-draft"><img src="https://agentmods.dev/badge/skills/alp82/aistack/news-draft.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.00836 |
| Opus 5 | $0.00012 | $0.00418 |
| Sonnet 5 | $0.00005 | $0.00167 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
news-draft 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 6d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
news-draft
Draft the news inbox. One run reads the undrafted items out of prod, reads the page behind each one, and writes one draft file per item. The owner reviews the files, merges them, and runs the apply command.
Nothing here writes to prod. The apply command is the only write path, and it runs after the owner has merged the files.
Spec: the Drafting section of docs/specs/news-pipeline.md. Decision:
docs/adr/0003-news-drafting-in-the-owner-session.md.
Steps
-
Read the work:
node scripts/news-drafts.ts listThe output is JSON:
items(the undrafted inbox rows),topics(the owner-managed list), andremaining(how many items sit past the batch limit). Add--limit Nto take a bigger or smaller batch.Stop here and say so when
itemsis empty. There is nothing to draft. -
Read the page behind every item. Dispatch one Explore subagent per item, all in one message so they run at once. Ask each for the facts of the page: what shipped or happened, who it is for, and the one number or name that matters.
Skip the subagent when the item already carries
sourceText. The collector kept the body because the license allowed it, so the text is already in front of you.Retry a page that fails, once. An item whose page still refuses stays undrafted, and the next run re-attempts it. Carry on with the rest.
-
Write the summary in your own words, three or four sentences. Say what changed and who it is for. Bytes is the editorial north star: plain, short, and specific.
Quote at most one short sentence from the page, and only from an item whose
licenseClassiscc-by,permissive-release-notes,article, orhn. The re-serving table in the spec says what each class permits. -
Pick one topic from
topics, by name.Ask the owner when no topic fits and you have a good candidate. Name the item, name the topic you propose, and wait for the answer. The topic list is owner-managed and it grows one topic at a time.
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.
- 6d ago First seen · 94 lines · 23 tokens per session scan A ec0e45e8bde6
news-draft is a skill published in the GitHub repository alp82/aistack (46 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 836 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 2026-08-30.
Other skills, from other repositories
a0-contribute-plugin
Guide for publishing an Agent Zero plugin to the community Plugin Index (a0-plugins repo). Covers GitHub repo setup, index.yaml creation, CI validation rules, and PR submission. Use when the user wants to share, publish, submit, or contribute a plugin to the Plugin Hub so other Agent Zero users can find and install it.
service-learning-project-designer
Design a service-learning project connecting genuine community need with embedded curriculum learning. Use when planning community projects, civic engagement, or social action units.
ubuntu-collective-knowledge-task-designer
Design learning tasks built on Ubuntu philosophy emphasising collective knowledge-building and mutual responsibility. Use when fostering collaboration that values community over individual competition.
place-based-curriculum-orchestrator
Present pathway options and orchestrate place-based curriculum design from a local place, curriculum requirement, or community issue. Use when place should become a primary text for learning.
init-agent-sync
Initializes the AGENTSYNC.md hub for AI agent coordination and task tracking.
wrap-phase
Wraps up a development phase by cleaning AGENTSYNC.md, summarizing work, and committing changes.