oh-my-hermes is an operating layer for Hermes Agent that organizes requests into workflows for planning, research, creation, coding handoffs, operations, and project memory. Hermes users run these workflows through the desktop app, CLI, or messenger app, while the catalogue add-ons extend its native capabilities.
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 rlaope/oh-my-hermes --skill omh-internal-auditgit clone --depth 1 https://github.com/rlaope/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/rlaope/oh-my-hermes/omh-internal-audit)<a href="https://agentmods.dev/skills/rlaope/oh-my-hermes/omh-internal-audit"><img src="https://agentmods.dev/badge/skills/rlaope/oh-my-hermes/omh-internal-audit/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/rlaope/oh-my-hermes/omh-internal-audit"><img src="https://agentmods.dev/badge/skills/rlaope/oh-my-hermes/omh-internal-audit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00097 | $0.01881 |
| Opus 5.5 | $0.00039 | $0.00752 |
| Sonnet 5.5 | $0.00019 | $0.00376 |
| Haiku 4.5 | $0.00010 | $0.00188 |
Grade A, and why
omh-internal-audit 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.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Internal Audit
This is an OMH internal-audit workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
Why This Exists
internal-audit exists because control-testing methodology had no owner: finance-analysis reports figures and names control exceptions, tech-debt-audit audits code, and production-audit audits a release, while population, sampling, re-performance, and deficiency severity had nothing that derived a grade from criteria.
First Steps
- Ask what the control is meant to prevent or detect, and over which population and period it operates.
- Ask for the sampling guidance and the materiality threshold before sizing any sample or grading anything.
Do Not Use When
- The ask is the month's figures, a budget variance, or the close itself; use
omh-finance-analysis. - The ask is reading a contract or a regulation for legal risk; use
omh-legal-compliance-review. - The ask is whether a service is ready to launch; use
omh-production-audit. - The ask is ranking a codebase's debt; use
omh-tech-debt-audit.
Examples
Good example:
- Prompt: we need to test the quarterly access review control for sox and grade what we find
- Expected behavior: Define the population of quarterly reviews for the period and check its completeness, size the sample from the quarterly frequency, request the signed review and the removal tickets per item, re-perform the comparison of access lists, and grade any deviation from stated likelihood, magnitude and compensating controls.
- Why: A grade that is not derived from criteria cannot be defended to an external auditor.
Bad example:
- Prompt: the owner says the control worked, just mark it effective
- Expected behavior: Refuse to conclude on inquiry alone: sample the population, obtain the evidence, and re-perform before any conclusion.
- Why: An owner's statement is the weakest evidence a control test can hold.
Completion Checklist
- The control, its population, and the completeness check are stated.
- The sample size is derived from stated frequency, confidence, and tolerable rate, and the selection can be redrawn.
- Each sample item names the evidence obtained, not described.
- Each item's re-performance result cites its evidence.
- The severity grade shows every criterion, or is withheld with the missing one named, and OMH signed off nothing.
What ships with it
1 file 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.
- 3d ago Changed · +1 lines 051c456a5270
- 16d ago Changed · +3 lines da42d3f5cb95
- 18d ago First seen · 135 lines · 97 tokens per session scan A 62e2b291bb4f
omh-internal-audit is a skill published in the GitHub repository rlaope/oh-my-hermes (3,392 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 1,881 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
levy
Domain knowledge agent for Japanese income tax filing (kakutei shinkoku). Guides income classification, deduction optimization, tax calculation, and filing for freelancers, sole proprietors, and side-business earners. Does not write code.
comps-valuation-analyst
Use when valuing a public company with peer multiples, building comparable-company tables, or pressure-testing a valuation range with EV/EBITDA, P/E, and EV/Sales.
earnings-call-analyzer
Use when summarizing earnings calls, extracting management tone changes, surfacing guidance language, or turning transcript snippets into an actionable investor update.
event-driven-tracker
Use when tracking earnings, product launches, M&A, dividends, buybacks, unlocks, or other market-moving dates that need a prioritized event calendar.
factor-backtester
Use when testing factor signals, running long-short spread backtests, checking hit rate and turnover, or sanity-checking whether a ranking signal survives basic transaction cost assumptions.
financial-analyst
Performs financial ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction for strategic decision-making.