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/jmstar85/oh-my-githubcopilot/deep-interviewnpx skills add jmstar85/oh-my-githubcopilot --skill deep-interviewgit clone --depth 1 https://github.com/jmstar85/oh-my-githubcopilotWhat 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 | $0.00057 | $0.01435 |
| Opus 5 | $0.00028 | $0.00718 |
| Sonnet 5 | $0.00011 | $0.00287 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade A, and why
deep-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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Interview
Ouroboros-inspired Socratic questioning with mathematical ambiguity scoring. Replaces vague ideas with crystal-clear specifications by asking targeted questions that expose hidden assumptions.
Pipeline
deep-interview → ralplan (consensus refinement) → omg-autopilot (execution)
When to Use
- User has a vague idea and wants thorough requirements gathering
- Task is complex enough that jumping to code would waste cycles
- User wants mathematically-validated clarity before execution
When NOT to Use
- Detailed specific request with file paths → execute directly
- Quick fix → delegate to @executor or
/ralph - User says "just do it" → respect their intent
Interactive Hook Protocol
MANDATORY: Use vscode_askQuestions for ALL user-facing questions in this skill (when available).
If vscode_askQuestions is NOT available (e.g., Copilot CLI), present numbered options in markdown and ask the user to respond with a number or freeform text.
This ensures structured input collection with selectable options, consistent UX, and clear decision tracking.
When to Fire Hooks
| Trigger Point | Question Type | Options Required |
|---|---|---|
| Phase 2 each round | Ambiguity-targeted question | 3-5 options + freeform |
| Phase 3 challenges | Assumption validation | Yes/No + "It depends..." |
| Phase 4 spec review | Confirm crystallized spec | Approve / Revise / Add constraints |
| Phase 5 execution bridge | Choose next workflow | 5 predefined options |
Hook Format Rules
- header: Short unique ID, e.g.
"interview-round-3","spec-approval" - question: The Socratic question targeting the weakest clarity dimension
- options: Provide 3-5 selectable answers that represent likely user intents
- First option: most common/expected answer (mark as
recommended) - Last option: always include an "Other / Let me explain..." escape hatch
- First option: most common/expected answer (mark as
- allowFreeformInput: Always
true— user can override any option with their own words - After receiving the answer, score ambiguity immediately and report progress
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 · 134 lines · 57 tokens per session scan A c50301674925
deep-interview is a skill published in the GitHub repository jmstar85/oh-my-githubcopilot (153 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 1,435 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 2026-08-30.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…