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/rubin-johnson/retro/agentic-interviewnpx skills add rubin-johnson/retro --skill agentic-interviewgit clone --depth 1 https://github.com/rubin-johnson/retroWrote 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/rubin-johnson/retro/agentic-interview)<a href="https://agentmods.dev/skills/rubin-johnson/retro/agentic-interview"><img src="https://agentmods.dev/badge/skills/rubin-johnson/retro/agentic-interview.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 | $0.00031 | $0.01392 |
| Opus 5 | $0.00015 | $0.00696 |
| Sonnet 5 | $0.00006 | $0.00278 |
| Haiku 4.5 | $0.00003 | $0.00139 |
Grade A, and why
agentic-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 4d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Interview
Interview methodology for logging errors and successes in agentic coding workflows. The goal: trace every outcome back to YOUR input -- what you prompted, what context you provided, what guardrails you set (or didn't).
Core Principle
The agent does what you tell it to. If the outcome was bad, the question is: what could YOU have done differently? Not "Claude messed up" -- that's a symptom. The root cause is always in the prompt, the context, the harness, or the meta-decisions around how you engaged.
Interview Methodology
Error Interviews
-
Review conversation context before asking anything. Look at what happened, what went wrong, and where the turning point was.
-
Ask 3-5 specific questions, one at a time. Adapt to the user's verbosity -- if they give detailed answers, ask fewer questions. If they're terse, probe deeper.
-
Always capture the triggering prompt verbatim. This is the single most valuable data point. Ask: "What exactly did you tell Claude before this went wrong? Can you paste or paraphrase the prompt?"
-
Propose a category -- don't ask the user to classify. Based on the conversation and answers, suggest: "This looks like a
prompt/missing-constraintsissue -- you told Claude what to do but not what NOT to do. Sound right?" Let them confirm or correct. -
Focus on the user's contribution. Every question should orient toward: "What could you have done differently in your prompt, context setup, or tool configuration to prevent this?"
Success Interviews
Same structure, adapted:
- Review what worked in the conversation.
- Ask 2-4 questions about what the user did that led to the good outcome.
- Capture the triggering prompt or technique verbatim.
- Propose a category.
- Focus on what's repeatable -- "What specifically about your approach made this work?"
Adapting Depth
- Verbose user: 2-3 focused questions, they're already giving you what you need.
- Terse user: 4-5 questions, probe for specifics. "Can you tell me more about what you expected vs what happened?"
- User provides optional description: Use it as a starting point, skip questions it already answers.
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.
- 4d ago First seen · 132 lines · 31 tokens per session scan A 05749a0477d3
agentic-interview is a skill published in the GitHub repository rubin-johnson/retro (2 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 1,392 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
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…