interview-writer

interview-writer is an agent for coding agents from nanparth/ai-skill-hub. It costs 0 tokens per session (941 once invoked), scanned A, original, MIT.

An agent that writes one fictional interview result from a fixed template and a defined persona. It fills in the answers while preserving the template’s headings, tables, and order.

In plain words
What is it for?
Use it to generate a completed interview transcript for a specified persona, using a skeleton file, allowed follow-ups, and formatting rules.
Why use it?
It provides a consistent way to create realistic sample interview data without changing the structure expected by later steps. Limiting follow-up questions to the supplied list keeps the result within the interview design.

Agent

Install

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.

agentmods
npx agentmods add agents/nanparth/ai-skill-hub/interview-writer
Clone the repo
git clone --depth 1 https://github.com/nanparth/ai-skill-hub

Wrote 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.

agentmods badge for interview-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nanparth/ai-skill-hub/interview-writer.svg)](https://agentmods.dev/agents/nanparth/ai-skill-hub/interview-writer)
Your own site
<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>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 941 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash 16bac7074c63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

biz-interview/agents/interview-writer.md · 46 lines

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

  1. Copy the skeleton structure exactly: title/header, Interviewee Info table, Key Points Summary, disclaimer (if present), all section headings, all question headings.
  2. Fill in the Interviewee Info table fields from the persona spec.
  3. Leave Key Points Summary bullets empty (dashes only).
  4. 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?").
  5. For free association (Q1): use the "Prompt" -- answer text format. One consolidated answer block per prompt. No dialogue format.
  6. If a Related section is present, use normal markdown links or plain filenames supplied by the user.
  7. Write the completed file to output_path.

Read the full file on GitHub · 46 lines

Changes

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.

  1. 5d ago First seen · 46 lines · 0 tokens per session scan A 16bac7074c63

Subscribe to this mod's changes

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.