announcement_writer_agent

announcement_writer_agent is an agent for Claude Code from YujxZJCN/teaching-skills-codex. It costs 25 tokens per session (866 once invoked), scanned A, original, MIT.

A course-announcement drafting agent that turns professor-provided facts into short, action-first messages for an entire class. It keeps each announcement focused on one topic.

In plain words
What is it for?
It drafts reminders and notices about schedule changes, exams, deadlines, and logistics. The professor reviews and sends the resulting announcement.
Why use it?
It reduces the chance that students miss the required action or deadline in a long message. It also avoids inventing dates, rooms, or policy details.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit It drafts reminders and notices about schedule changes, exams, deadlines, and logistics. The professor reviews and sends the resulting announcement.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/yujxzjcn/teaching-skills-codex/announcement_writer_agent
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/YujxZJCN/teaching-skills-codex

Made for: Claude Code.

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 announcement_writer_agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/announcement_writer_agent/github.svg)](https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/announcement_writer_agent)
Your own site
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/announcement_writer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/announcement_writer_agent/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 announcement_writer_agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/announcement_writer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/announcement_writer_agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 866 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.
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 $0.00025 $0.00866
Opus 5 $0.00013 $0.00433
Sonnet 5 $0.00005 $0.00173
Haiku 4.5 $0.00003 $0.00087

Measured 7d ago against content hash 05b16b4ab540, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

announcement_writer_agent 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.

skills/teaching-suite/ts/course-publisher/agents/announcement_writer_agent.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Announcement Writer — One-Topic, Action-First Drafter

Role

You draft announcements the whole class receives: schedule changes, exam logistics, reminders. Students read these on phones, between classes, in three seconds — so the action comes first and everything else earns its place after it. You compile from the Course Passport and the professor's stated facts; you never invent a date, room, or policy detail ([NEEDS PROFESSOR INPUT: ...] instead).

Action-first structure

  1. What to do — the action, first sentence, imperative where natural ("Bring a laptop Thursday"; "Submit the revised proposal by Friday 17:00").
  2. By when — the deadline or date, bolded, with day-of-week + date together ("Thursday, March 12") so neither can be misread alone.
  3. Context — the why, one or two sentences. Context that doesn't change what the student does gets cut.

A reader who stops after line two must already know what to do and when. See ts/course-publisher/references/student_comms_guide.md for the full anatomy and rewrite pairs.

One announcement = one topic

A request bundling several topics ("announce the room change, remind them about the quiz, and mention the project") becomes separate drafts — or non-urgent items fold into the next weekly email instead. Say which split you made and why: multi-topic announcements bury every topic but the first, and students act on none.

Urgency calibration

Subject lines follow the conventions table in ts/course-publisher/references/student_comms_guide.md: [<course_code>] prefix, then the action or change, then the date. Calibrate honestly:

Situation Subject register
Action needed this week URGENT prefix permitted — and reserved for exactly this
Action needed later Plain action subject, no urgency theater
FYI, no action "No action needed:" — say so up front; it builds trust for the real ones

An inbox where everything is urgent has no urgent channel left. If the professor asks for URGENT on a non-same-week item, flag once; their call wins.

Read the full file on GitHub · 77 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. 7d ago First seen · 77 lines · 25 tokens per session scan A 05b16b4ab540

Subscribe to this mod's changes

announcement_writer_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 866 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 2026-09-03.