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/genkovich/sdd/interviewnpx skills add genkovich/sdd --skill interviewgit clone --depth 1 https://github.com/genkovich/sddWhat 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 | $0.00202 | $0.01915 |
| Opus 5 | $0.00101 | $0.00958 |
| Sonnet 5 | $0.00040 | $0.00383 |
| Haiku 4.5 | $0.00020 | $0.00192 |
Grade A, and why
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 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: interview
Pressure-tests an idea before it becomes a spec. The user shares a raw idea; across 3
phases you surface hidden assumptions, name tradeoffs, expose imprecisions, and propose
fresh angles — then hand the survivor to specify. This is the optional pre-backbone step:
it makes specify cheaper by killing or reshaping a weak idea before any spec gets written.
Scope: any idea. Product, content, business, architecture, refactor approach — all in scope. The boundary: this is an interview about the idea, not codebase archaeology. Ask the user to articulate the idea in words first. Consult files only if the user explicitly invites it; default is interview-first, no unprompted grep/find/read.
Language. Respond in the user's language; the instructions here are English for clarity.
The depth dial and the Socratic posture are SDD-wide:
→ ../_shared/interview-depth.md · ../_shared/ask-style.md
Depth dial — set this first
One AskUserQuestion, then commit (default medium). The dial is SDD-wide; interview's
delta — the 3–4 / 6–10 / 10–15 question budget per level and each level's posture — is the
canonical interview row in ../_shared/interview-depth.md
(no table duplicated here).
The adversarial triggers (grill / rip apart / розʼєби / погрилити) imply hard unless the user says otherwise. State the depth in one line, then start.
Hard rules
- Every question goes through AskUserQuestion, not free text — 2-4 concrete options, the
first marked
(Recommended), each option'sdescriptionspelling out what follows from it. Free text slips into "I don't know" and loses signal. - One question at a time. The user answers with full context on the previous answer, and you adapt the next question to it.
- Recommendation is mandatory. Always carry a position inside the Recommended option — a neutral interviewer surfaces less than one with a take the user can argue against.
- Don't skip phases. No alternatives before intent is clear; no grilling tradeoffs before the idea is understood.
What ships with it
2 files 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.
- 2d ago First seen · 152 lines · 202 tokens per session scan A 115b5c5485e7
interview is a skill published in the GitHub repository genkovich/sdd (118 stars, last pushed 13d ago), licensed MIT. It adds 202 tokens to every session and 1,915 once invoked, about $0.0010 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.