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.
git clone --depth 1 https://github.com/YujxZJCN/teaching-skills-codexWrote 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/agents/yujxzjcn/teaching-skills-codex/lecture_writer_agent)<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.
<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>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 | $0.00021 | $0.00845 |
| Opus 5 | $0.00010 | $0.00423 |
| Sonnet 5 | $0.00004 | $0.00169 |
| Haiku 4.5 | $0.00002 | $0.00085 |
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.
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
- Read the source material: the confirmed arc (segments, minutes, the one idea per
segment, outcomes served),
learner_profile— especiallyknown_difficulties— and any source material the professor supplied (past notes, textbook chapters, papers). Professor-supplied material is the preferred basis for every domain claim. - 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)
- Anticipate misconceptions: for each concept, check
known_difficultiesfrom 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. - 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. - 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.
- Hand off: notes keyed to segment IDs, plus the consolidated [VERIFY] list for Phase 3 assembly.
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 · 63 lines · 21 tokens per session scan A 081b6922e613
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.
Other agents, from other repositories
evidence_assembler_agent
Assembles the evidence package behind a confirmed matrix — inventories what exists with provenance, lists what's missing with the cheapest honest fix; never fabricates data.
matrix_builder_agent
Builds and maintains the LO × program-outcome × criterion mapping matrix — professor-claimed strengths, computed per-cell evidence status, hollow-cell and over-mapping flags.
selfstudy_writer_agent
Drafts self-study and continuous-improvement sections from the confirmed matrix + evidence index — claim strength capped by evidence status, every factual sentence traceable.
standards_analyst_agent
Normalizes professor-supplied standards and program outcomes into a criteria register — verbatim text, evidence type demanded, vague-criterion flags.
accommodation_designer_agent
Operationalizes an already-granted accommodation into modified assessment materials with equivalent rigor — never decides eligibility, never names the condition.
grade_analyst_agent
Closes the gradebook: final-grade distribution with shape diagnostics, a what-if cutoff/curve comparator, and a fairness note — aggregates only, the professor sets cutoffs.