Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add archugunov/pm-job-search/plugin install pm-job-searchWrote 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/skills/archugunov/pm-job-search/case-practice)<a href="https://agentmods.dev/skills/archugunov/pm-job-search/case-practice"><img src="https://agentmods.dev/badge/skills/archugunov/pm-job-search/case-practice/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/skills/archugunov/pm-job-search/case-practice"><img src="https://agentmods.dev/badge/skills/archugunov/pm-job-search/case-practice.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 | $0.00170 | $0.02738 |
| Opus 5 | $0.00085 | $0.01369 |
| Sonnet 5 | $0.00034 | $0.00548 |
| Haiku 4.5 | $0.00017 | $0.00274 |
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 11d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/case-practice — MC rapid-recognition drill
This is drill 1 — MC rapid-recognition — of the case-practice methodology, and it's the first rung of a five-drill ladder. Its job is to lock the recognition of senior-vs-junior answers and build the vocabulary every later drill needs: you can't fix a gap you don't have the language to name. It runs as batches of single-select questions, scores each pick with the specific failure mode behind every wrong option, tracks a running score against an 80% readiness gate, and extracts anchors to memorise. See ${CLAUDE_PLUGIN_ROOT}/references/case-interviews/practice-methodology.md for the full five-drill ladder (recognition → generation → performance) and why the order matters. The live mock (drill 4) runs via the interviewer-simulator agent — only after the user clears the ≥80% gate here.
Voice: follows ${CLAUDE_PLUGIN_ROOT}/TONE.md. Low-effort-first — start on context-weighted defaults; don't interrogate the user about scope, depth, or case types before the first batch. If a <Company> argument is given, theme from it silently (read the company's files, weight the mix, theme products) — no confirmation question.
MC-able case types (what the drill draws from)
MC recognition only fits atomic, discriminable judgement calls — "pick the strongest of four" where exactly one option is right and the rest each fail for a nameable reason. It does NOT fit open-ended strategy, technical / system-design, or estimation cases: those are free-form / live-mock territory (drills 2 and 4) and are out of scope for this drill. Don't generate MC questions for them.
The drill samples from:
- Product sense — strongest NSM; the right segment + a clean pick-reason; JTBD need quality. This is the richest seam — weight it heaviest by default.
- Metric movement — the correct first diagnostic fork (drop-to-diagnose vs goal-to-hit); MECE-clean vs overlapping decomposition.
- Metric tree — the 4-part NSM form (unit + behaviour + threshold + cadence); guardrail vs counter-metric vs vanity metric.
- Prioritisation — which lens fits the situation; "define value before you score"; spotting the sycophancy / spreadsheet-obeying trap.
- Behavioural — spotting the seniority signal (rejected-options / named trade-off / honest retrospective) vs the junior tell (heroics, no failure named, wrong altitude).
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.
- 11d ago First seen · 102 lines · 170 tokens per session scan A f8f23c7fe39b
case-practice is a skill published in the GitHub repository archugunov/pm-job-search (7 stars, last pushed 15d ago), licensed MIT. It adds 170 tokens to every session and 2,738 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
interview
Produce a tailored interview prep sheet (behavioral, technical, system design, company) from a job description and the user's resume.
tutorial
Interactive walkthrough for new users. Learn by doing — each step creates real content in your vault. Three tracks (researcher, manager, personal) with a universal learning arc. Triggers on "/tutorial", "walk me through", "how do I use this".
learn
Research a topic and grow your knowledge graph. Uses Exa deep researcher, web search, or basic search to investigate topics, files results with full provenance, and chains to processing pipeline. Triggers on "/learn", "/learn [topic]", "research this", "find out about".
course-builder
Use whenever the user wants to ingest a new course's materials (lecture notes, textbook chapters, HW problems, HW solutions) and build the course-specific knowledge base — patterns.md (recurring solution techniques), coverage.md (HW-to-section map with 🔥 exam tiers + ⚠weak flags), and summary.md (topic tree). Invoked…
alt-import
Parse an Exam Radar (OPTIMETA Alt plugin) export and fold its lecture-emphasis exam-probability signal into the PAIDEIA course index — write course-index/radar.md, annotate course-index/coverage.md with a lecture-emphasis column and divergence flags, and seed a gold-zone weakmap. Invoked by /paideia:alt. The export…
mock-interview
Mock interviewer — role-plays a hiring-bar interviewer for an interactive mock interview, asking one question at a time, drilling deeper adaptively, scoring in real time, and identifying weak spots. Company styles are loaded from your configurable company-style library.