interview

An interactive interview that collects the details needed to define a software story and saves them in an interview file.

In plain words
What is it for?
It helps gather scope, API needs, design decisions, constraints, and information from related project documents for a selected story.
Why use it?
It turns incomplete ideas into recorded context before the story’s specification, mockups, API design, or tests are created.

Skill for Claude CodeCodex

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 skills/rakovi4/continue-framework/interview
Any agent
npx skills add rakovi4/continue-framework --skill interview
Clone the repo
git clone --depth 1 https://github.com/rakovi4/continue-framework

Made for: Claude Code, Codex.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,127 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00050 $0.01127
Opus 5 $0.00025 $0.00563
Sonnet 5 $0.00010 $0.00225
Haiku 4.5 $0.00005 $0.00113

Measured 2d ago against content hash 7d4b2d132672, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

interview scanned grade B with 1 finding 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 2d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

6. **A named precedent, if this story has one**: the `interview.md` or `decisions/*-decision.md` of the *specific* earlier story whose decision this one extends or contradicts — under `stories/` or `stories/done/`, and m
.claude/skills/interview/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate interview.md via Interactive Interview

Conduct a structured interview with the user to gather all context needed for a story, then generate the interview.md file that feeds into the story spec step (dispatched by /continue), /mockups, /api-spec, /test-spec.

Usage

/interview 5                    # By MVP story number
/interview "Create task"             # By story name
/interview                      # Interactive selection

Workflow

Phase 1: Context Gathering (Silent)

Before asking any questions, silently read. Resolve the target story first (Phase 2's parse step) — items 4, 6, 9 and 10 are scoped to it and cannot be read before it is known:

  1. Story mapping: ProductSpecification/stories.md
  2. Product description: ProductSpecification/BriefProductDescription.md
  3. Expected load: ProductSpecification/ExpectedLoad.md
  4. Existing story spec (if any): ProductSpecification/stories/NN-story-name/NN_StoryName.md
  5. Archived drafts: ProductSpecification/Archived/DraftStories/1st-iteration/ (scan for relevant files)
  6. A named precedent, if this story has one: the interview.md or decisions/*-decision.md of the specific earlier story whose decision this one extends or contradicts — under stories/ or stories/done/, and most often the latter, since a story with a settled decision is usually closed (.claude/rules/workflow.md, "Resolving a story folder"). Never all stories/*/interview.md — that sweep reconstructs the present from a pile of deltas; item 9 answers that question instead. Asking whether a precedent exists at all has its own permitted form — a keyword-scoped grep across stories/** including done/ (.claude/rules/workflow.md, "Asking whether a non-goal or a rationale exists is not the banned sweep")
  7. Existing domain code: Scan backend/domain/src/ and backend/usecase/src/
  8. Existing adapters: Scan backend/adapters/*/src/
  9. What the areas this story touches already do: the acceptance tests of those areas — test class names, scenario descriptions, Statements. This is the current state, not the story folders (.claude/rules/workflow.md, "Where the Current State Lives"). Only enabled tests count as shipped — one still carrying its disable/skip marker is a pending increment, not shipped behavior. Where the suite is silent about an area, read that area's production code and say so in the interview — items 7-8 for a backend behavior, the frontend source for a UI-only one, which Phase 1 does not otherwise scan; silence is not evidence of absence. In a repo with no acceptance suite yet, say so explicitly and fall back to the story folders
  10. Existing test cases doc (if any): ProductSpecification/stories/NN-story-name/tests/01_API_Tests.md

Read the full file on GitHub · 70 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. 2d ago First seen · 70 lines · 50 tokens per session scan B 7d4b2d132672

Subscribe to this mod's changes

interview is a skill published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 5d ago), licensed MIT. It adds 50 tokens to every session and 1,127 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens