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/mkonstan/llm-tools/interviewnpx skills add mkonstan/llm-tools --skill interviewgit clone --depth 1 https://github.com/mkonstan/llm-toolsWhat 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 | $0.00189 | $0.02774 |
| Opus 5 | $0.00095 | $0.01387 |
| Sonnet 5 | $0.00038 | $0.00555 |
| Haiku 4.5 | $0.00019 | $0.00277 |
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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview: Adversarial Knowledge Extraction
Extract tacit knowledge from humans through structured adversarial interviewing. Produces knowledge artifacts (context dumps, KBs, specs, decision logs) shaped by what the interview surfaces — including what the human didn't know they hadn't said.
Before Starting
Read references as needed during the interview:
references/probe_challenge_catalog.md— Probe types, challenge types, blind spot techniques, provenance tagsreferences/friction_calibration.md— Too soft / too hard signals, depth vs breadth, session pacing, failure modesreferences/output_mapping.md— Output format selection, context dump mapping, quality metrics
The Core Problem
Collaborative extraction fails. The human says what they know, you write it down, both agree, and the gaps never surface. First answers are rehearsed, not examined. The human doesn't know what they haven't said. Agreement feels like progress but produces shallow artifacts.
Adversarial extraction treats the first answer as the starting point, not the deliverable. The value is in friction — pushback that surfaces what the human knows but hasn't said, believes but hasn't examined, or assumes but hasn't validated.
When To Use
- Domain onboarding: Human has context, you have none
- Requirements gathering: Human knows what they want but hasn't fully articulated it
- Decision documentation: Decisions were made but rationale is implicit
- Knowledge transfer: Context must be captured from a human
- Pre-build scoping: Extract the full problem space before committing to architecture
- Context dump bootstrapping: Need a seed artifact from a cold start
The Protocol
Phase 0: Orient
Do not start interviewing until Orient is complete.
Determine:
- What domain? What world does this knowledge live in?
- What's the goal? What will the extracted knowledge be used for?
- What artifact? What output format serves the goal? (See
references/output_mapping.md) - What's the human's role? Domain expert, decision-maker, operator, stakeholder?
- What's the knowledge type? Procedural (how), structural (what), decisional (why), or mixed?
What ships with it
3 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 · 264 lines · 189 tokens per session scan A b3c39489f2e0
interview is a skill published in the GitHub repository mkonstan/llm-tools (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 189 tokens to every session and 2,774 once invoked, about $0.0009 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
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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…