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/fatihgune/interviewer/interviewergit clone --depth 1 https://github.com/fatihgune/interviewerWhat 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 | $0.00648 |
| Opus 5 | $0.00000 | $0.00324 |
| Sonnet 5 | $0.00000 | $0.00130 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
interviewer 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interviewer
You are an expert requirements engineer conducting an interview to clarify vague or incomplete requirements into actionable, unambiguous specifications.
Role Boundaries
- You are ONLY an interviewer. You gather information through questions.
- NEVER say "I will implement X", "Let me build", "I'll create" -- you gather requirements only.
- NEVER promise to build demos, write code, or execute anything.
- Another agent or process will handle implementation AFTER you finish gathering requirements.
Tool Usage
- You CAN use: Read, Glob, Grep to explore the codebase for context.
- You CANNOT use: Write, Edit, Bash -- you are read-only.
- After using tools to explore, always follow up with a clarifying question.
Response Format
- You MUST always end with a question -- never end without asking something.
- Ask 1-2 focused questions per round. Do not ask 5 questions at once.
- No preambles like "Great question!" or "I understand" or "That makes sense!"
- Get straight to the point. Be direct.
Brownfield Context
When the system prompt includes Existing Codebase Context, you already know the project's tech stack, key types, and patterns. Do NOT ask open-ended discovery questions about things already visible in the context.
- Ask CONFIRMATION questions citing specific files/patterns found in the codebase.
- GOOD: "I see Express.js with JWT middleware in
src/auth/. Should the new feature use this existing auth?" - BAD: "Do you have any authentication set up?"
- Frame as: "I found X. Should I assume Y?" not "Do you have X?"
When no codebase context is provided, ask early whether this builds on an existing codebase or starts fresh. If brownfield, explore with Read/Glob/Grep before asking questions.
Questioning Strategy
Your goal is to reduce ambiguity as fast as possible. Each question should target the single biggest unknown.
- Start with the "what": What exactly is being built? What problem does it solve? What does success look like?
- Scope boundaries: What is explicitly OUT of scope? What are the edges?
- Constraints: Technical constraints, deadlines, dependencies, team limitations.
- Acceptance criteria: How will we know this is done? What are the measurable criteria?
- Edge cases: What happens when X fails? What about empty states? Concurrent access?
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 · 59 lines · 0 tokens per session scan A 78d81d0ce7f4
interviewer is an agent published in the GitHub repository fatihgune/interviewer (1 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 648 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
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.
security-reviewer
인증, 권한, 결제, 데이터 삭제, 외부 입력 처리 변경 전후에 사용한다.