interview-plan

interview-plan is a command for Claude Code from primeline-ai/universal-planning-framework. It costs 12 tokens per session (1,515 once invoked), scanned A, original, MIT.

A command that asks structured questions about a development plan at three levels of detail.

In plain words
What is it for?
Use it to interview a plan interactively, or to have the tool answer its own questions when strengthening a plan automatically.
Why use it?
It helps uncover important gaps and weak assumptions that a quick plan review may overlook.

Command for Claude Code

Part of the universal-planning-framework plugin — 2 skills, 4 commands, 1 agent shipped together

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 commands/primeline-ai/universal-planning-framework/interview-plan
Clone the repo
git clone --depth 1 https://github.com/primeline-ai/universal-planning-framework

Made for: Claude Code.

Or install universal-planning-framework, the plugin that ships this one along with the rest of its 2 skills, 4 commands, 1 agent.

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-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/primeline-ai/universal-planning-framework/interview-plan.svg)](https://agentmods.dev/commands/primeline-ai/universal-planning-framework/interview-plan)
Your own site
<a href="https://agentmods.dev/commands/primeline-ai/universal-planning-framework/interview-plan"><img src="https://agentmods.dev/badge/commands/primeline-ai/universal-planning-framework/interview-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,515 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 $0.00012 $0.01515
Opus 5 $0.00006 $0.00758
Sonnet 5 $0.00002 $0.00303
Haiku 4.5 $0.00001 $0.00152

Measured 4d ago against content hash a7e3df16504b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interview-plan 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 4d 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.

.claude/commands/interview-plan.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Interview

You are interviewing this plan: $ARGUMENTS

Read the plan file and conduct a framework-aware interview. Questions are generated based on the Universal Planning Framework, not generic templates.


Mode Selection

Interactive mode (default): Ask the user questions via AskUserQuestion, one tier at a time.

Self-interview mode (--self flag): Claude answers its own questions autonomously. Useful for hardening a plan without human input. Write answers directly, flag low-confidence answers with [Low confidence].


Pre-Flight

  1. Read the plan file using the Read tool
  2. Detect domain: Software, AI/Agent, Business, Content, Infrastructure, Data & Analytics, Research, Multi-Domain
  3. Identify plan grade: Check which CORE/CONDITIONAL sections exist, estimate current grade (C/B/A)
  4. Scan for anti-patterns: Quick check against 21 anti-patterns to inform question generation

Question Generation (3 Tiers)

Tier 1: Critical Gaps (ask first)

Questions about missing or weak CORE sections. These block implementation.

Gap Type Example Question
Missing FAILED conditions "What kills this project? After how long without progress do you pull the plug?"
Vague success criteria "You say 'improve performance' - what specific number makes this a success vs. failure?"
Unvalidated assumptions "You assume [X] - how will you verify this before Phase [N] depends on it?"
No rollback on irreversible change "If Phase [N] breaks production, what's the undo plan? How long does rollback take?"
Missing VALIDATE BY "Assumption [X] has no validation method. How would you test this cheaply before committing?"
Assumed facts (#21) "You state [X] as fact - is this verified or an assumption? What's the source?"
Premature commitment "For assumption [X], what alternative interpretation haven't you considered? Could [X] mean something different than you think?"

Read the full file on GitHub · 145 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. 4d ago First seen · 145 lines · 0 tokens per session scan A a7e3df16504b

Subscribe to this mod's changes

interview-plan is a command published in the GitHub repository primeline-ai/universal-planning-framework (45 stars, last pushed 10d ago), licensed MIT. It adds 12 tokens to every session and 1,515 once invoked, about $0.0001 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 2026-08-30.