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 skills add witt3rd/oh-my-hermes --skill omh-deep-interviewgit clone --depth 1 https://github.com/witt3rd/oh-my-hermesWrote 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/witt3rd/oh-my-hermes/omh-deep-interview)<a href="https://agentmods.dev/skills/witt3rd/oh-my-hermes/omh-deep-interview"><img src="https://agentmods.dev/badge/skills/witt3rd/oh-my-hermes/omh-deep-interview/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/witt3rd/oh-my-hermes/omh-deep-interview"><img src="https://agentmods.dev/badge/skills/witt3rd/oh-my-hermes/omh-deep-interview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00018 | $0.02746 |
| Opus 5 | $0.00009 | $0.01373 |
| Sonnet 5 | $0.00004 | $0.00549 |
| Haiku 4.5 | $0.00002 | $0.00275 |
Grade A, and why
omh-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 10d 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.
OMH Deep Interview — Requirements Specification Through Conversation
When to Use
- The goal is vague, underspecified, or could be interpreted multiple ways
- Before planning (omh-ralplan) or implementation on non-trivial work
- The user says: "deep interview", "requirements", "what should we build", "help me think through this"
- omh-ralplan determines the goal is too ambiguous to plan
- You're unsure what the user actually wants
- Domain unfamiliarity: if the goal requires external knowledge of an unfamiliar domain, suggest running
omh-deep-researchfirst to gather context, then resume the interview with the confirmed report as input.
When NOT to Use
- The goal is already crystal clear and bounded
- A confirmed spec already exists in
.omh/specs/for this project - The user explicitly wants to skip requirements gathering
- Trivial single-file changes where the task is obvious
Prerequisites
- Conversational access to the user (this skill asks questions and needs answers)
- Write access to
.omh/directory for state and spec files
Procedure
Follow these phases in order. The skill operates through conversation with the user and file writes for state and spec output.
Phase 0: Check for Existing State
Before starting a new interview:
- Enumerate active interviews:
Each entry carrieslisted = omh_state(action="list_instances", mode="interview")instance_id(the interview id) andactiveflag. Ifomh_stateis unavailable, glob.omh/state/interview--*.jsonmanually. - If any active interview exists, tell the user: "There's an active interview for '{project_name}' (id={id}). Resume, start fresh, or abandon it?"
- If resuming:
omh_state(action="read", mode="interview", instance_id="{id}")— read round summaries to reconstruct context - If abandoning:
omh_state(action="write", mode="interview", instance_id="{id}", data={...status: "abandoned"}), then proceed to Phase 1 with a NEW id - If no active state found: proceed to Phase 1
- Concurrent interviews on different projects are permitted; do not block.
- Check for existing research context (omh-deep-research sentinel):
if any
.omh/research/*-report.mdexists with frontmatterstatus: confirmed, mention it to the user as available context for the interview (e.g., "I see a confirmed research report on '{topic}' at{path}— want me to fold that in as background?"). Do NOT auto-load it; the user decides.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 242 lines · 18 tokens per session scan A a2600bba5087
omh-deep-interview is a skill published in the GitHub repository witt3rd/oh-my-hermes (321 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 2,746 once invoked, about $0.0001 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…