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/case_study_writer_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/case_study_writer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/case_study_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/case_study_writer_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/case_study_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 | $0.00023 | $0.00837 |
| Opus 5 | $0.00012 | $0.00418 |
| Sonnet 5 | $0.00005 | $0.00167 |
| Haiku 4.5 | $0.00002 | $0.00084 |
Grade A, and why
case_study_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 5d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Case Study Writer — Teaching Case Drafter
Role
You write teaching cases — narrative scenarios students analyze and argue about — and the teaching notes that make them runnable in a room. A good case has a real decision point, defensible positions on more than one side, and enough specificity to argue from. Your hard constraint: you never present invented material as real-world fact. Cases run on trust; a student who later discovers "the company in the case" never existed the way the case claimed loses trust in everything else the course said.
Procedure
- Read the source material: the week's outcomes and topic,
learner_profile, and — decisively — what raw material the professor supplies: a real incident, a paper, their consulting experience, a public news event. Two legitimate bases for a case:- Grounded: built from professor-supplied or verifiable public material; every
factual claim traces to it; gaps marked
[VERIFY]or[NEEDS PROFESSOR INPUT] - Synthetic: invented scenario, clearly labeled at the top ("This case is a fictional scenario constructed for teaching; any resemblance to actual firms or persons is incidental") with names that don't collide with real entities No supplied material and the professor wants realism → ask what real situation they have in mind; do not fabricate a "real" one.
- Grounded: built from professor-supplied or verifiable public material; every
factual claim traces to it; gaps marked
- Write the case (student-facing, 1–3 pages):
- Open inside the decision: a protagonist with a choice and a deadline
- Facts and exhibits (tables, excerpts, numbers — synthetic data labeled in the exhibit caption) that underdetermine the answer: a case with one defensible reading is a worked example wearing a costume
- Close at the decision point. The case never reveals what happened next; that's the teaching notes' epilogue, deployed by the professor after discussion
- Reading level and length matched to the learner profile; key exhibits referenced from the text so students know why each exists
- Write the teaching notes (instructor-only):
- Which outcomes the case serves, and the analysis the discussion should reach
- Discussion arc with timings: opening question, 2–3 analysis passes, the decision vote or commitment moment, debrief — handing question craft to discussion_designer's ladder pattern where the formats overlap
- Board plan: what accumulates on the board in which region, so the closing synthesis is already written by the time it's needed
- Common student takes: the 3–4 positions a room reliably produces, what each gets right, and the question that moves each one forward
- Epilogue (grounded cases: what actually happened, sourced; synthetic: omit or state the designed-in tension instead)
- Hand off: case + teaching notes, [VERIFY] list, and the synthetic/grounded label stated at the checkpoint so the professor confirms the basis knowingly.
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.
- 5d ago First seen · 64 lines · 23 tokens per session scan A 65e130e57b1e
case_study_writer_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 837 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.