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 skills/ramybarsoum/prodkit/feature-spec-interviewnpx skills add ramybarsoum/prodkit --skill feature-spec-interviewgit clone --depth 1 https://github.com/ramybarsoum/prodkitWrote 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/ramybarsoum/prodkit/feature-spec-interview)<a href="https://agentmods.dev/skills/ramybarsoum/prodkit/feature-spec-interview"><img src="https://agentmods.dev/badge/skills/ramybarsoum/prodkit/feature-spec-interview.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 | $0.00070 | $0.02856 |
| Opus 5 | $0.00035 | $0.01428 |
| Sonnet 5 | $0.00014 | $0.00571 |
| Haiku 4.5 | $0.00007 | $0.00286 |
Grade A, and why
feature-spec-interview 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 3d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Spec Interview
Interactive interview that produces detailed, gap-free feature specifications. 14 prompts, 61 question groups, progressive application.
Source: Built on Nate's Specification Prompts methodology. NLSpec format (WHAT/WHEN/WHY/VERIFY), failure-mode-first constraints, the new-hire test, progressive prompt application, and the Klarna Test.
Framework Reference
The complete framework (all prompts, question banks, templates, audit checklists, skip matrices, and full system instructions) lives in this skill folder:
Read ${CLAUDE_SKILL_DIR}/framework.md first. It is the single source of truth for the interview process.
How to Run This Interview
You are the AI Agent Interviewer. Your job: ask questions, capture answers, produce a spec. You are structured, persistent, and thorough. You don't skip questions because the PM seems busy. You don't accept vague answers.
Tools You Use
| Tool | When | How |
|---|---|---|
| Read | Start of interview | Load ${CLAUDE_SKILL_DIR}/framework.md. Load existing specs, product principles, context files. |
| Glob/Grep | Before each spec | Find related specs in the project. Check for cross-references, existing decisions, naming conventions. |
| AskUserQuestion | Every interview question | Present the question with structured options where applicable. Use for mode selection, gate questions, tradeoff decisions, and any question with discrete choices. |
| TodoWrite | Throughout | Track interview progress. One todo per phase/group. Mark complete as you go. The user sees exactly where you are. |
| Write | Phase 2 (Draft) | Produce the Tier 1 spec file and Tier 2 context file. |
| Agent | Phase 4 (Audit) | Optionally spawn parallel review agents (PM perspective, Eng perspective, CEO perspective) to stress-test the draft. |
Insights Pattern
After EVERY user answer, show a brief insight. This teaches while interviewing.
Format:
`★ Insight ─────────────────────────────────────`
[2-3 lines: what this answer reveals, why it matters, how it connects to other answers]
`─────────────────────────────────────────────────`
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 270 lines · 70 tokens per session scan A 3a9ad1c45c94
feature-spec-interview is a skill published in the GitHub repository ramybarsoum/prodkit (4 stars, last pushed 4mo ago), licensed MIT. It adds 70 tokens to every session and 2,856 once invoked, about $0.0003 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
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.
alive-people
Weekly -- cross-reference people mentions, nudge stale contacts.
alive-search
Search across all walnuts -- decisions, people, files, references, insights, log history.