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/ramsbaby/jarvis/deep-interviewnpx skills add Ramsbaby/jarvis --skill deep-interviewgit clone --depth 1 https://github.com/Ramsbaby/jarvisWrote 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/ramsbaby/jarvis/deep-interview)<a href="https://agentmods.dev/skills/ramsbaby/jarvis/deep-interview"><img src="https://agentmods.dev/badge/skills/ramsbaby/jarvis/deep-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 | $0.00069 | $0.00786 |
| Opus 5 | $0.00034 | $0.00393 |
| Sonnet 5 | $0.00014 | $0.00157 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
jarvis-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 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/deep-interview — Convergent Requirements Interview
Acts as a senior architect. 8-15 rounds of Socratic questions narrow a vague idea into a production-grade spec. Blocks contradictions, edge-case gaps, and security gaps before any code is written.
How it differs from /brainstorm
- /brainstorm (divergent): expand possibilities. 15-20 questions + UI mockup variants. Exits when ideation feels saturated.
- /deep-interview (convergent): spec gating. 8-15 narrowing rounds + decision log. Exits when ambiguity score ≤ threshold.
When to use which:
- Idea itself is undefined →
/brainstorm - Idea exists, implementation decisions are undefined →
/deep-interview
Mechanism (4 stages)
1. Mathematical ambiguity gating
After each round, score across:
- Undefined behavior areas
- Contradiction risk (conflicting requirements)
- Uncovered edge cases
- Security gaps (secrets, PII, permissions)
- Unidentified irreversible decisions
Refuse autonomous implementation until score ≤ 0.2 (default threshold).
2. Socratic question patterns
Examples the agent will ask:
- "What happens when X scenario triggers Y?"
- "What evidence would prove this decision wrong (falsifiability condition)?"
- "What assumptions are you carrying that aren't yet stated?"
- "What technical debt will this create one year out?"
3. Contrarian / Simplifier Challenge Mode
For each major decision, automatically run two checks:
- Contrarian: deliberately raise the counter-hypothesis (debiasing — never confirm a single hypothesis without testing its opposite)
- Simplifier: check whether a much smaller version exists (Karpathy "Simplicity First" — 200 lines vs 50 lines)
4. Decision log auto-write
All decisions, rationale, falsifiability conditions, and challenge results are recorded in JSONL for later audit.
Iron rules integration
- No fix without root cause: 5-why on each decision
- Never lie about status: "don't know" is explicitly marked, not papered over
- User sovereignty: agent questions are strong signals, not commands — user's answer is final
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 · 82 lines · 69 tokens per session scan A e941caa68b78
jarvis-deep-interview is a skill published in the GitHub repository Ramsbaby/jarvis (16 stars, last pushed 12d ago), licensed MIT. It adds 69 tokens to every session and 786 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
debug-evals
Debug haiku.rag evaluation runs in Logfire. Use when asked to look at Logfire for an eval run, find failing or low-scoring eval cases, compare runs, check citation quality (citedmap) or judge pass rate (answerequivalent), or explain why an eval case failed. Drives the Logfire MCP against the evals service, or the…
hyperframes
Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation…
hyperframes-cli
HyperFrames CLI tool — hyperframes init, lint, preview, render, transcribe, tts, doctor, browser, info, upgrade, compositions, docs, benchmark. Use when scaffolding a project, linting or validating compositions, previewing in the studio, rendering to video, transcribing audio, generating TTS, or troubleshooting the…
architecture-design
Orchestrate an architectural concept workflow across Rhino, Blender, and ComfyUI connectors.
validation
Use when Codex is already in the validation phase of a security scan or the user explicitly asks to determine whether one or more candidate security findings are valid. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.
fix-finding
Use when the user explicitly asks to fix and verify a validated or plausible security finding. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.