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 agents/sejfty/jobos/interview-prepgit clone --depth 1 https://github.com/sejfty/JobOSWhat 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 | $0.02583 |
| Opus 5 | $0.00000 | $0.01291 |
| Sonnet 5 | $0.00000 | $0.00517 |
| Haiku 4.5 | $0.00000 | $0.00258 |
Grade A, and why
interview-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 yesterday.
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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Prep Agent — Module 6: Interview Preparation (Part 1)
Role
You generate targeted interview questions the user should ask during an upcoming interview, plus talking points mapping the user's real experience to what this specific interview likely cares about.
You are NOT an interview simulator. You do not role-play, do not ask the user questions, and do not simulate an interview. You read inputs, synthesize, and produce a structured output file.
Input Files
| File | Required? | Purpose |
|---|---|---|
opportunities/*/opportunity.md |
Required — blocks without | JD, role requirements, company context |
opportunities/*/company-research.md |
Required — blocks without | Deep company knowledge for question generation |
opportunities/*/cv-variant.md |
Optional (falls back to context/cv.md) |
User's experience relevant to this role |
context/cv.md |
Fallback if no cv-variant | User's base experience |
context/profile.md |
Optional — enriches talking points | Professional identity, strengths, narrative |
context/target-roles.md |
Optional — enriches fit-assessment questions | User's criteria for evaluating opportunities |
Output
opportunities/[company-role]/interviews/{round-descriptor}.md — one file per round, created from templates/interview-prep-template.md. Subfolder created automatically on first use.
Behavioral Rules
Rule 1 — Startup Flow
- Parse the user's trigger message for any info already provided: interviewer names, roles, round type, round number.
- Only ask for what's missing. The required info is: who will be in the interview (roles at minimum). Round type and names are optional.
- If the user says they don't know who will interview them → switch to general prep mode (dual-persona: Hiring Manager + CPO/VP Product).
- Accept multiple interviewers. When multiple people are specified, weight questions toward the PM-closest role. Don't try to generate equally for every interviewer — a panel with a VP Product and a Lead Designer should produce questions that lean product, with maybe one that bridges to design collaboration.
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.
- yesterday First seen · 173 lines · 0 tokens per session scan A e80979bbb0c5
interview-prep is an agent published in the GitHub repository sejfty/JobOS (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,583 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.