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/orenluxy/fable-method/interview-menpx skills add orenluxy/fable-method --skill interview-megit clone --depth 1 https://github.com/orenluxy/fable-methodWhat 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 | $0.00069 | $0.00499 |
| Opus 5 | $0.00034 | $0.00249 |
| Sonnet 5 | $0.00014 | $0.00100 |
| Haiku 4.5 | $0.00007 | $0.00050 |
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 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.
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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Me
Purpose: convert the user's unknown knowns (implicit preferences and constraints they have but didn't state) into known knowns — cheaply, before implementation makes them expensive.
Rules
-
One question per message. Never batch. The user's answer to question N should be allowed to change question N+1.
-
Prioritize by architectural impact. Ask first the questions whose answers would change the structure of the solution. Cosmetic and naming questions come last or not at all. Before asking anything, internally rank your candidate questions by: "if the answer surprises me, how much of the design changes?"
-
Every question must be paired with your current best guess. Format: state the question, then "My default if you don't care: X, because Y." This lets the user answer with one word ("default") and keeps the interview fast.
-
Hard cap: 7 questions. If you have more than 7, your top 7 by architectural impact. If you genuinely can't get below 7, that's a signal the task should be split — say so.
-
Stop early. The moment remaining questions are all low-impact, say "Remaining questions are cosmetic — I'll use sensible defaults and log them in IMPLEMENTATION_NOTES.md" and end the interview.
-
Close with a contract. After the last answer, output a short summary: decisions made, defaults assumed, and the rewritten task statement. Ask for a single confirmation before implementing.
Mid-implementation use
This skill also applies DURING implementation: when you hit an unknown whose resolution would change already-written code by more than ~20 lines, pause and ask rather than guess. For smaller unknowns, take the conservative option and log it under Deviations in IMPLEMENTATION_NOTES.md (see the implementation-notes skill).
Anti-patterns
- Twenty trivia questions is failure. Fewer, sharper questions win.
- Asking questions whose answers are discoverable in the codebase or via search is failure. Look first, ask only what only the user knows.
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.
- 2d ago First seen · 32 lines · 69 tokens per session scan A c5d8f7e4a2f5
interview-me is a skill published in the GitHub repository orenluxy/fable-method (1 stars, last pushed 26d ago), licensed MIT. It adds 69 tokens to every session and 499 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
workflow
Professional AI programming assistant with structured workflow (Research -> Ideate -> Plan -> Execute -> Optimize -> Review) for developers.
git-rollback
Interactively rollback Git branch to historical version; lists branches, versions, then executes reset/revert after confirmation.
golden-rss
Use when testing the rss golden build.
design-system-builder
Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want to create consistent designs, generate design systems, or build MVP UIs matching reference aesthetics.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…