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.
Borrowing it
Nothing to install: this file belongs to rlaope/oh-my-hermes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rlaope/oh-my-hermes/main/AGENTS.mdgit 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/instructions/rlaope/oh-my-hermes/agents-md)<a href="https://agentmods.dev/instructions/rlaope/oh-my-hermes/agents-md"><img src="https://agentmods.dev/badge/instructions/rlaope/oh-my-hermes/agents-md/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/instructions/rlaope/oh-my-hermes/agents-md"><img src="https://agentmods.dev/badge/instructions/rlaope/oh-my-hermes/agents-md.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 | $0.08435 | $0.08435 |
| Opus 5.5 | $0.03374 | $0.03374 |
| Sonnet 5.5 | $0.01687 | $0.01687 |
| Haiku 4.5 | $0.00843 | $0.00843 |
Grade B, and why
oh-my-hermes AGENTS.md scanned grade B with 2 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 yesterday.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo install, a clarify with no question in it, or a method it does not Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`narrate.py` (ElevenLabs TTS/STT/SFX/music by spawning `curl`, key from How it starts
The opening of the file, as written. The whole thing — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OMH Agent Contract
This file is the repo-local operating contract for coding agents working on oh-my-hermes, including Codex, Claude Code, Hermes runtime/handoff paths, and generic executor profiles.
Product Direction
Read docs/DIRECTION.md before changing architecture, workflow behavior,
wrapper contracts, generated skill guidance, or coding delegation semantics.
OMH is a Hermes-native wrapper orchestration layer. Keep Hermes responsible for chat intake, clarification, source-backed research, planning, and status narration. Keep main coding work delegated to the selected coding owner through explicit prepared handoffs and observed evidence. Do not make Codex the implicit default in product language, docs, schemas, prompts, or reports when Claude Code, Hermes runtime/handoff paths, or generic executor profiles are also valid owners.
When developing OMH itself, treat Codex, Claude Code, and Hermes runtime/handoff paths as first-class product surfaces. User-facing runtime selection may choose one coding owner for a task, but OMH feature design, contracts, docs, setup, memory recall, and status/reporting changes should consider all three surfaces unless a change is explicitly scoped to one executor. If support differs, document the difference as a capability boundary instead of silently optimizing for Codex.
Do not turn OMH into a hidden Hermes runtime patch, transport bot, network
service, LLM router, or secret coding executor. The one sanctioned execution
surface is the explicit opt-in fanout dispatch bridge described under
Implementation Boundaries — operator-invoked, local-only, fully observed,
never hidden and never a default. The one sanctioned network call OMH makes is
the omh_jev_ask tool, also described there — user-requested per turn, never a
default. The show-reel toolkit's opt-in provider scripts reach a provider
only when the user runs them with their own key; OMH never runs them. The OMH TUI that bare omh opens is a terminal frontend over Hermes'
own gateway, not an execution surface; its boundary is stated there too,
including its gateway child, which on Hermes' interpreter reaches the person's
own gateway over loopback as Hermes' own TUI does.
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.
- yesterday Changed · +46 lines · +845 tokens per session 2c4b5a1cc10a
- 2d ago Changed · +43 lines · +808 tokens per session 38f75d376f98
- 3d ago Changed · +2 lines · +34 tokens per session 4ce5654de6e4
- 7d ago Changed · -1 lines · -22 tokens per session 9d3ad4b56f91
- 8d ago Changed · +22 lines · +384 tokens per session bcad59ccdd1d
- 9d ago Changed · +42 lines · +724 tokens per session scan A → B 066ac59da3aa
- 10d ago Changed · +70 lines · +1,286 tokens per session 640e0d030337
- 28d ago Changed · +3 lines · +50 tokens per session d16befad73cc
- 1mo ago Changed · +20 lines · +374 tokens per session fb13df46b21a
- 1mo ago First seen · 347 lines · 3,952 tokens per session scan A c1c284d3b5b2
oh-my-hermes AGENTS.md is an instructions file published in the GitHub repository rlaope/oh-my-hermes (3,912 stars, last pushed today), licensed MIT. It adds 8,435 tokens to every session, about $0.0337 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.