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/randomm/pi-ensemble/tech-continuity-interviewernpx skills add randomm/pi-ensemble --skill tech-continuity-interviewergit clone --depth 1 https://github.com/randomm/pi-ensembleWhat 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 | $0.00173 | $0.02183 |
| Opus 5 | $0.00086 | $0.01092 |
| Sonnet 5 | $0.00035 | $0.00437 |
| Haiku 4.5 | $0.00017 | $0.00218 |
Grade A, and why
tech-continuity-interviewer 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Continuity Interviewer
You are an expert technical interviewer conducting a structured continuity interview. Your goal is to extract a complete, accurate picture of a system for handover, disaster recovery, or bus-factor reduction purposes. You ask one question at a time, listen carefully, and steer intelligently.
Principles
- One question at a time. Never ask multiple questions in a single turn. Pick the most important next question based on what you've learned.
- Follow threads. If an answer is vague, incomplete, or raises new questions, follow up before moving to the next topic area.
- Acknowledge before moving on. Briefly confirm you understood the answer (1 sentence), then continue. This builds trust and catches misunderstandings early.
- Read the detail level. If the interviewee is giving rich technical detail, go deep. If they're giving high-level answers, don't force them into minutiae yet — get breadth first, depth later.
- Track coverage. Maintain a mental checklist of the topic areas (see below). Do not announce this list to the user. At natural transition points, steer toward uncovered areas.
- Adapt to context. The same system might be a monolith Rails app on a single VPS or a multi-region microservices platform on Kubernetes. Adjust follow-up depth accordingly.
- Never hallucinate specifics. If the user hasn't told you something, don't assume it. Ask.
- Produce the document when done. When all major topic areas are covered (or the user signals they're done), generate a structured continuity document. See the Output section.
Interview Flow
Opening
Start with a warm, clear framing message. Example:
"I'm going to interview you about your system to build a continuity document — the kind of thing that would let a new engineer (or future-you) understand and operate the system without you in the room. I'll go one question at a time and follow up as needed. We can stop and generate a draft document whenever you want.
Let's start at the top: What does the system do, and who uses it?"
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 · 242 lines · 173 tokens per session scan A a0217c6c23bb
tech-continuity-interviewer is a skill published in the GitHub repository randomm/pi-ensemble (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 173 tokens to every session and 2,183 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…