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-researchgit 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-research)<a href="https://agentmods.dev/skills/witt3rd/oh-my-hermes/omh-deep-research"><img src="https://agentmods.dev/badge/skills/witt3rd/oh-my-hermes/omh-deep-research/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-research"><img src="https://agentmods.dev/badge/skills/witt3rd/oh-my-hermes/omh-deep-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 293 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
- medium Rogue Agent · line 55 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00019 | $0.04380 |
| Opus 5 | $0.00010 | $0.02190 |
| Sonnet 5 | $0.00004 | $0.00876 |
| Haiku 4.5 | $0.00002 | $0.00438 |
Grade A, and why
omh-deep-research 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 11d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OMH Deep Research — Multi-Phase Web Research with Citation Verification
When to Use
- The user asks for "deep research on", "a research report about", "comprehensive research", "investigate X", "what's known about Y"
- omh-deep-interview encounters an unfamiliar domain and needs background
- omh-ralplan needs external context before it can plan responsibly
- The user's question requires synthesizing 3+ web sources into one coherent answer, not a single search
When NOT to Use
- A confirmed report already exists at
.omh/research/{slug}-report.mdwithstatus: confirmedfor this topic — view it instead - The question is answerable by a single web_search call
- The user wants real-time / current-events data only (this skill emphasizes durable synthesis, not freshness)
- No
webtoolset is available in this Hermes install (see Prerequisites)
Prerequisites
This skill fail-fasts if any of the following are missing:
webtoolset — providesweb_searchANDweb_extract. If either is unavailable, print:
and exit before doing any work.omh-deep-research requires the `web` toolset (web_search + web_extract); aborting.omh_statetool — preferred path. If absent, fall back to manual JSON read/write at.omh/state/research--{slug}.json(per-instance —{slug}is the kebab+date+random4 minted in Phase 1; multiple research topics can run concurrently). If neither is writable, fail-fast with a clear error.- Write access to
.omh/for state, plan, findings, report, log.
Hermes discovery: hermes skills list | grep omh-deep-research should
return this skill once installed.
Installation (symlink for Hermes discovery)
mkdir -p ~/.hermes/skills/omh && ln -snf <repo>/plugins/omh/skills/omh-deep-research ~/.hermes/skills/omh/omh-deep-research
Parent dir creation MUST precede the symlink.
Architecture
Five invocation phases, exit-safe between any two:
| # | Phase | Reads | Writes | Subagents |
|---|---|---|---|---|
| 1 | decompose | user query | {slug}-plan.md, state.phase=search |
none |
| 2 | search | plan, state, findings/ | new findings file(s), state.completed_subtopics, phase | 1-3 [omh-role:researcher] parallel |
| 3 | gap_check | all findings | optional _followup.md OR direct phase flip |
0 or 1 [omh-role:researcher] |
| 4 | synthesize | all findings (parent inlines) | {slug}-report.md status: draft, phase=verify |
1 [omh-role:research-synthesist] |
| 5 | verify | report + findings (parent inlines) | confirmed frontmatter / state mutate / blocked | 1 [omh-role:research-verifier] |
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.
- 11d ago First seen · 369 lines · 19 tokens per session scan A fb4b1d0c91bb
omh-deep-research is a skill published in the GitHub repository witt3rd/oh-my-hermes (322 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 4,380 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…