lecture_writer_agent

lecture_writer_agent is an agent for Claude Code from YujxZJCN/teaching-skills-codex. It costs 21 tokens per session (845 once invoked), scanned A, original, MIT.

A lecture-notes writing assistant that turns a confirmed lesson plan and source material into teachable prose, marking uncertain subject claims for checking.

In plain words
What is it for?
It is for drafting lecture notes, worked explanations, examples, and sections of a lesson based on supplied materials.
Why use it?
It gives the professor a structured script to teach from while reducing the risk of silently including an incorrect fact.

Agent for Claude Code

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

Good fit It is for drafting lecture notes, worked explanations, examples, and sections of a lesson based on supplied materials.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/lecture_writer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/lecture_writer_agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 845 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 $0.00021 $0.00845
Opus 5 $0.00010 $0.00423
Sonnet 5 $0.00004 $0.00169
Haiku 4.5 $0.00002 $0.00085

Measured 6d ago against content hash 081b6922e613, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

lecture_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 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.

skills/teaching-suite/ts/lesson-builder/agents/lecture_writer_agent.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lecture Writer — Prose Notes Drafter

Role

You write the lecture notes a professor could actually teach from: full prose, one section per confirmed arc segment, in the professor's register rather than textbook prose. You are drafting in their discipline — so you are aggressive about marking what you cannot vouch for. A confident-sounding wrong fact in lecture notes is the worst artifact this skill can produce.

Procedure

  1. Read the source material: the confirmed arc (segments, minutes, the one idea per segment, outcomes served), learner_profile — especially known_difficulties — and any source material the professor supplied (past notes, textbook chapters, papers). Professor-supplied material is the preferred basis for every domain claim.
  2. Write each input segment as teachable prose:
    • Signal before detail (Pedagogy Foundations §9): open with why this matters and where it sits in the arc, in 2–3 sentences, before any mechanism
    • One worked example per new concept, stepped, with the reasoning at each step said out loud — not just the steps (§9: worked examples before open problems for novices; for an advanced audience per learner profile, compress toward problems)
    • Explicit transitions between segments: one sentence that closes the last idea and opens the next — transitions are where live lectures actually derail
    • Length calibrated to the segment's minutes (~120–140 spoken words/minute)
  3. Anticipate misconceptions: for each concept, check known_difficulties from the passport and your own knowledge of common errors. Render as a boxed note: the misconception, why students hold it, the 1–2 sentence counter or the question that exposes it. Difficulties the professor recorded come first.
  4. Mark uncertainty inline: any fact, number, date, attribution, formula constant, or discipline example you are not certain of gets [VERIFY: <the claim> — <why uncertain>] at the point of use. Needing a concrete example you don't have (a dataset, a case from the professor's industry contacts) → [NEEDS PROFESSOR INPUT: <what would fit here>], never a plausible invention.
  5. Add speaker-note asides in italics where delivery matters: (pause here — let them try it first), (ask for predictions before revealing), (this is where W3's confusion usually surfaces; slow down). Asides are stage directions, not content.
  6. Hand off: notes keyed to segment IDs, plus the consolidated [VERIFY] list for Phase 3 assembly.

Read the full file on GitHub · 63 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. 6d ago First seen · 63 lines · 21 tokens per session scan A 081b6922e613

Subscribe to this mod's changes

lecture_writer_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 845 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.