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 skills add GuillemRoca/agent-skills-android --skill interview-megit clone --depth 1 https://github.com/GuillemRoca/agent-skills-androidWrote 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/guillemroca/agent-skills-android/interview-me)<a href="https://agentmods.dev/skills/guillemroca/agent-skills-android/interview-me"><img src="https://agentmods.dev/badge/skills/guillemroca/agent-skills-android/interview-me.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 5.1 | $0.00047 | $0.01186 |
| Opus 5 | $0.00023 | $0.00593 |
| Sonnet 5 | $0.00009 | $0.00237 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
interview-me 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 7d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Me
Overview
The cheapest bug is the one never written because the right question was asked first. This skill replaces assumption-stacking with a structured interview: ask targeted questions in small batches, feed each answer into the next round, and stop only when you could write the spec's acceptance criteria without inventing anything. It front-loads the conversation that otherwise happens as review rework.
When to Use
- The request is one or two sentences for something clearly bigger ("add offline support")
- Requirements contradict each other or the existing app's behavior
- Multiple plausible interpretations exist and picking wrong is expensive
- Before
spec-driven-developmentwhen the input idea is fuzzy - A stakeholder says "you know what I mean" — you don't
Skip when: The task is small and unambiguous (rename, obvious bug fix), or a spec with acceptance criteria already exists — go build. Don't interview to avoid starting.
Core Process
Step 1: State What You Think You Know
- Write down the current understanding and confidence level before asking anything:
## Understanding: offline support for tasks
- Users can view cached tasks offline — confident (stated)
- Users can CREATE tasks offline — assumed, not stated
- Conflict resolution strategy — unknown
- Sync trigger (foreground only? WorkManager?) — unknown
Confidence: ~40%
Unknowns and assumptions become the question list. If nothing lands in those rows, you didn't need the interview.
Step 2: Ask in Small, Targeted Batches
- 3–5 questions per round, highest-leverage first. One decision per question, concrete options over open prompts:
1. When a task is edited offline on two devices, which wins — last write,
or surface a conflict to the user?
2. Should offline creation work, or is offline read-only for v1?
3. Sync on app-open only, or background sync via WorkManager?
4. What happens to offline changes if the user logs out?
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.
- 7d ago First seen · 110 lines · 47 tokens per session scan A 66bd1b57c628
interview-me is a skill published in the GitHub repository GuillemRoca/agent-skills-android (2 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,186 once invoked, about $0.0002 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
spec-kitty-mission-system
Understand how Spec Kitty missions work: the 4 built-in mission types, how they define workflows via step contracts and action indices, how missions and work packages relate, how templates are resolved through the 6-tier chain, and how doctrine artifacts (procedures, tactics, directives) compose mission behavior.…
spec-kitty-git-workflow
Understand how Spec Kitty manages git: what git operations Python handles automatically, what agents must do manually, worktree lifecycle, auto-commit behavior, merge execution, and the safe-commit pattern. Triggers: "how does spec-kitty use git", "worktree management", "auto-commit", "who commits what", "git…
spec-kitty-spdd-reasons
Drive REASONS Canvas authoring and review for Spec Kitty missions that opted in to Structured-Prompt-Driven Development (SPDD) via charter selection. Triggers: "use SPDD", "use REASONS", "generate a REASONS canvas", "apply structured prompt driven development", "make this mission SPDD". Does NOT handle: enforcing SPDD…
spec-kitty-runtime-review
Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback. Triggers: "review this work package", "check runtime output", "approve this step", "review WP", "is this WP ready to approve", "check this implementation". Does NOT handle: setup-only…
spk-doctrine-show-me
Explain Spec Kitty work with compact, checkable visuals. Use for specs, plans, architecture, control flow, diffs, status boards, or whenever prose obscures structure.
spk-admin-dashboard
Open or report the Spec Kitty dashboard. Use for dashboard URL, localhost daemon metadata in .kittify/.dashboard, --open, --kill, or status views.