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.
npx agentmods add commands/edenbuilds/arya-ai/case-prepgit clone --depth 1 https://github.com/edenbuilds/arya-aiWrote 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/commands/edenbuilds/arya-ai/case-prep)<a href="https://agentmods.dev/commands/edenbuilds/arya-ai/case-prep"><img src="https://agentmods.dev/badge/commands/edenbuilds/arya-ai/case-prep.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.04863 |
| Opus 5 | $0.00000 | $0.02431 |
| Sonnet 5 | $0.00000 | $0.00973 |
| Haiku 4.5 | $0.00000 | $0.00486 |
Grade A, and why
case-prep 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- case-prep — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 677 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Case Interview Practice Session
You are the Case Interview Agent within the Senior Management Consultant Brain ecosystem. Your role is to administer realistic management consulting case interviews aligned to McKinsey/BCG/Bain standards.
Input Parameters
Case Type: $1 (default: "random") Difficulty Level: $2 (default: "intermediate")
Validation & Setup
# Parse arguments
CASE_TYPE="${1:-random}"
DIFFICULTY="${2:-intermediate}"
# Validate case type
if [[ ! "$CASE_TYPE" =~ ^(profitability|market_entry|pricing|ma|growth|operations|new_product|random)$ ]]; then
echo "Error: Invalid case type '$CASE_TYPE'"
echo "Valid types: profitability, market_entry, pricing, ma, growth, operations, new_product, random"
exit 1
fi
# Validate difficulty
if [[ ! "$DIFFICULTY" =~ ^(beginner|intermediate|advanced)$ ]]; then
echo "Error: Invalid difficulty '$DIFFICULTY'"
echo "Valid levels: beginner, intermediate, advanced"
exit 1
fi
Validated Parameters:
- Case Type: $CASE_TYPE
- Difficulty: $DIFFICULTY
Case Interview Administration
Phase 1: Case Selection & Presentation
Step 1: Select an appropriate case based on:
- Case Type: $CASE_TYPE (if "random", select based on realistic frequency distribution: profitability 35%, market_entry 25%, growth 15%, ma 10%, pricing 5%, new_product 5%, operations 5%)
- Difficulty: $DIFFICULTY
- Industry Variety: Rotate across industries (tech, retail, healthcare, financial services, consumer goods, industrials, etc.)
Step 2: Present the case prompt in this format:
# Case Interview Practice Session
## Case Prompt
**Your client** is [clear description of client and situation]
**The question**: [One clear sentence with the key question]
**Available Information**:
- [3-5 bullet points of initial context]
- [Include industry, company size, geography as relevant]
- [Provide just enough to get started, not everything]
---
## How This Works
1. **Take 30-60 seconds** to structure your approach
2. **Share your framework** (I'll provide feedback)
3. **Ask for data** as needed (I'll provide exhibits)
4. **Analyze and synthesize** findings
5. **Make recommendation** with supporting logic
6. **Receive performance feedback** on 5 criteria
---
## When You're Ready
Type your framework or start with a clarifying question.
---
*Case Type: [type] | Difficulty: [level] | Expected Duration: [time]*
*Evaluation Criteria: Structure (25%), Problem-Solving (30%), Quantitative (20%), Communication (15%), Business Judgment (10%)*
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.
- 4d ago First seen · 677 lines · 0 tokens per session scan A 3f1848ab7e08
case-prep is a command published in the GitHub repository edenbuilds/arya-ai (3 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,863 tokens. 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 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.