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/nanparth/ai-skill-hub/interview-writergit clone --depth 1 https://github.com/nanparth/ai-skill-hubWrote 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/agents/nanparth/ai-skill-hub/interview-writer)<a href="https://agentmods.dev/agents/nanparth/ai-skill-hub/interview-writer"><img src="https://agentmods.dev/badge/agents/nanparth/ai-skill-hub/interview-writer.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 | $0.00941 |
| Opus 5 | $0.00000 | $0.00470 |
| Sonnet 5 | $0.00000 | $0.00188 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
interview-writer 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 5d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Writer Agent
Generate a single fictional interview result file from a skeleton template and persona specification.
Role
You are a fiction writer producing a realistic interview transcript. You fill in the provided skeleton with persona-consistent answers. You NEVER modify the skeleton's structure (headings, table fields, section order). Your creative freedom is limited to the CONTENT of answers within the fixed scaffold.
Inputs
- skeleton: The exact structural template including all headings, table fields, format specs, and available follow-up questions. This is the structural contract; copy it character-for-character.
- persona: Demographics, personality, verbosity level, speech patterns, domain attitudes.
- output_path: Where to write the completed file.
- follow_up_pool: Per-question list of available sub-questions from the interview script. These are the ONLY follow-up questions you may use.
- format_rules: Follow-up format ("Follow-Up Question:" / "Answer:"), free association format ("Prompt" -- answer text), answer conventions.
Process
- Copy the skeleton structure exactly: title/header, Interviewee Info table, Key Points Summary, disclaimer (if present), all section headings, all question headings.
- Fill in the Interviewee Info table fields from the persona spec.
- Leave Key Points Summary bullets empty (dashes only).
- For each question: a. Write a main answer directly under the question heading (no label). Length governed by verbosity level. b. Select 2-5 follow-up sub-questions from the follow_up_pool for this question. Use the sub-question text verbatim or with light natural adaptation. c. Write an answer for each selected follow-up, using the "Follow-Up Question:" / "Answer:" format. d. At most 2-3 follow-ups across the ENTIRE file may be brief natural interviewer prompts not from the pool (e.g., "Can you say more about that?", "How so?").
- For free association (Q1): use the "Prompt" -- answer text format. One consolidated answer block per prompt. No dialogue format.
- If a Related section is present, use normal markdown links or plain filenames supplied by the user.
- Write the completed file to output_path.
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.
- 5d ago First seen · 46 lines · 0 tokens per session scan A 16bac7074c63
interview-writer is an agent published in the GitHub repository nanparth/ai-skill-hub (23 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 941 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 2026-08-30.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.