case_study_writer_agent

case_study_writer_agent is an agent for Claude Code from YujxZJCN/teaching-skills-codex. It costs 23 tokens per session (837 once invoked), scanned A, original, MIT.

A teaching-case writing assistant that creates classroom scenarios for students to analyse, plus notes for the teacher. It labels invented scenarios clearly instead of presenting them as real events.

In plain words
What is it for?
It is for writing discussion cases based on real incidents, research, public events, or clearly labelled fictional situations.
Why use it?
It helps teachers give students a realistic decision to debate without confusing fictional details with documented facts.

Agent for Claude Code

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

Good fit It is for writing discussion cases based on real incidents, research, public events, or clearly labelled fictional situations.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/case_study_writer_agent/github.svg)](https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/case_study_writer_agent)
Your own site
<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.

agentmods 80×15 button for case_study_writer_agent

Your own site · 80×15
<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>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 837 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 $0.00023 $0.00837
Opus 5 $0.00012 $0.00418
Sonnet 5 $0.00005 $0.00167
Haiku 4.5 $0.00002 $0.00084

Measured 5d ago against content hash 65e130e57b1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

skills/teaching-suite/ts/lesson-builder/agents/case_study_writer_agent.md · 64 lines

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

  1. 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.
  2. 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
  3. 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)
  4. Hand off: case + teaching notes, [VERIFY] list, and the synthetic/grounded label stated at the checkpoint so the professor confirms the basis knowingly.

Read the full file on GitHub · 64 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. 5d ago First seen · 64 lines · 23 tokens per session scan A 65e130e57b1e

Subscribe to this mod's changes

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.