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/zereight/gitlab-mcp/deep-interviewnpx skills add zereight/gitlab-mcp --skill deep-interviewgit clone --depth 1 https://github.com/zereight/gitlab-mcpWhat 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 | $0.00713 |
| Opus 5 | $0.00028 | $0.00357 |
| Sonnet 5 | $0.00011 | $0.00143 |
| Haiku 4.5 | $0.00006 | $0.00071 |
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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- deep-interview — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 76 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
Phases
Phase 1: Initialize
- Parse the user's idea
- Detect brownfield vs greenfield (use @explore to check codebase)
- For brownfield: map relevant codebase areas
- Initialize ambiguity score at 100%
Phase 2: Interview Loop
Repeat until ambiguity <= 20% or user exits early:
- Generate question targeting the WEAKEST clarity dimension
- Ask ONE question at a time with current ambiguity context
- Score ambiguity across dimensions:
- Goal Clarity (40% weight for greenfield, 35% brownfield)
- Constraint Clarity (30% / 25%)
- Success Criteria (30% / 25%)
- Context Clarity (N/A / 15% for brownfield)
- Report progress with dimension scores and gaps
- Track ontology (key entities, stability ratio)
Phase 3: Challenge Agents
- Round 4+: Contrarian - challenge core assumptions
- Round 6+: Simplifier - probe for complexity removal
- Round 8+: Ontologist - find the essence (if ambiguity > 30%)
Phase 4: Crystallize Spec
When ambiguity <= threshold, generate spec to .omc/specs/deep-interview-{slug}.md:
- Goal, Constraints, Non-Goals, Acceptance Criteria
- Assumptions Exposed & Resolved
- Ontology (Key Entities) with convergence tracking
- Interview Transcript
Phase 5: Execution Bridge
Present options:
- Ralplan → OMG Autopilot (Recommended): consensus-refine then execute
- Execute with omg-autopilot (skip ralplan)
- Execute with ralph: persistence loop
- Execute with team: parallel agents
- Refine further: continue interviewing
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.
- 3d ago First seen · 76 lines · 57 tokens per session scan A 16daa80ebb49
deep-interview is a skill published in the GitHub repository zereight/gitlab-mcp (1,939 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 713 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.
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…