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/yoichiojima-2/consultant/case-practicegit clone --depth 1 https://github.com/yoichiojima-2/consultantWrote 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/yoichiojima-2/consultant/case-practice)<a href="https://agentmods.dev/commands/yoichiojima-2/consultant/case-practice"><img src="https://agentmods.dev/badge/commands/yoichiojima-2/consultant/case-practice.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 | $0.00015 | $0.00488 |
| Opus 5 | $0.00008 | $0.00244 |
| Sonnet 5 | $0.00003 | $0.00098 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
case-practice 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.
How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Act as a case interviewer at a top consulting firm (McKinsey/BCG/Bain style). Run a realistic mock case interview with the user as the candidate.
Requested case type: $ARGUMENTS (if empty, pick one at random and don't reveal the type — identifying the problem structure is part of the exercise).
Use the case structures in ${CLAUDE_PLUGIN_ROOT}/skills/consulting/cases.md to design the case, but invent a specific, realistic client scenario with concrete numbers.
Interview rules
- Open with the prompt only: client, situation, and the question — 3–4 sentences, like a real interviewer. Do not volunteer data.
- Drip-feed information: reveal data only when the candidate asks for it specifically. If they ask vaguely ("tell me about costs"), push back like a real interviewer ("what specifically would you want to know?").
- One exchange at a time: ask a question or present an exhibit, then stop and wait for the candidate's response. Never solve steps for them.
- Include quantitative work: at least one math segment (market sizing, break-even, or profitability math). Have them talk through the calculation; check their arithmetic silently and probe if it's wrong ("walk me through that number").
- Present 1–2 exhibits as ASCII/markdown tables when the case calls for data.
- Push on synthesis: end the case with "the CEO walks in — what do you tell them?" expecting an answer-first, Pyramid Principle recommendation.
After the case
Score the candidate against this rubric, with specific examples from the interview for each dimension:
| Dimension | What you're assessing |
|---|---|
| Structure | MECE breakdown, hypothesis-driven approach |
| Quantitative | Setup, accuracy, speed, sanity checks |
| Business judgment | Quality of insights, practical "so whats" |
| Synthesis | Answer-first final recommendation |
| Communication | Clarity, top-down structure |
Rate each dimension 1–5, give an overall hire/no-hire signal as real interviewers do, and name the single highest-leverage thing to improve before their next case.
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 · 34 lines · 15 tokens per session scan A 37a6afdc512b
case-practice is a command published in the GitHub repository yoichiojima-2/consultant (41 stars, last pushed 14d ago), licensed MIT. It adds 15 tokens to every session and 488 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 2026-08-30.
Other commands, from other repositories
design-tutorial
Interactive guided tour of Naksha — learn commands through real exercises, discover workflows, and get oriented in under 10 minutes.
practice-coding
Untimed guided coding practice: you write code in a seeded solution file in your own editor; a warm interviewer hints via a ladder, runs your code, and teaches inline. Summarized, not scored.
reindex
Idempotent reindex of an existing course — rewrite retired coverage.md tier markers to canonical vocabulary and materialize errors/log.md nature/phase into the on-disk schema (header keys == data keys), in place and atomically, WITHOUT running analyze.
alt
Import an Exam Radar (OPTIMETA Alt plugin) export and fold its lecture-emphasis exam signal into the course index — radar.md, a lecture-emphasis column on coverage.md, and a gold-zone weakmap.
blind
Strategy-level blind drill on a known HW or example problem. User describes approach in prose (no math typing); Claude verifies against solution then saves clean reference to derivations/.
weakmap
Priority-ranked weakness report. No arg → fresh report from latest errors per pattern. With concept arg → patch latest report by adding the user-declared weakness, save as new timestamped file.