Agent skill

Omh Agent Instructions

by rlaope in rlaope/oh-my-hermes

[omh] Agent instruction file for a repo -- AGENTS.md, CLAUDE.md, a Cursor rule: write or update what an agent cannot derive from the code, inside a marked region, with every command verified or…

MITAuto-check passedAgent Workflows

Install Omh Agent Instructions

skills CLI
$ npx skills add rlaope/oh-my-hermes --skill omh-agent-instructions -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install rlaope/oh-my-hermes omh-agent-instructions --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/rlaope/oh-my-hermes.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/omh-agent-instructions .claude/skills/omh-agent-instructions && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
omh-agent-instructions
GitHub stars
3.2k
Token cost
~2.2k tokens
SKILL.md length
1,075 words
Files
2 (incl. references)
Skills in repo
143
Repo updated
First seen
Licence
MIT

At a glance

[omh] Agent instruction file for a repo -- AGENTS.md, CLAUDE.md, a Cursor rule: write or update what an agent cannot derive from the code, inside a marked region, with every command verified or…

  • The user says: agent-instructions
  • SKILL.md covers Why This Exists, First Steps, Do Not Use When and Examples, plus 6 more sections
  • Calls cursor
  • Copilot-instructions.md

What it does

Omh Agent Instructions is an agent skill from rlaope/oh-my-hermes. [omh] Agent instruction file for a repo -- AGENTS.md, CLAUDE.md, a Cursor rule: write or update what an agent cannot derive from the code, inside a marked region, with every command verified or marked unverified and no counts that drift. Use when the user says: agent-instructions, agents.md, claude.md, gemini.md, copilot-instructions.md, .cursorrules, cursor rules, cursor rule.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/instruction-file-method.md`).

It sits in Agent Workflows, covering Agent instruction files. The repository describes itself as: All in one plugin for Hermes Agent ⚚ the coding intelligence, a long-term memory system and model optimized workflow packages. The licence is MIT.

When your agent uses it

  • The user says: agent-instructions
  • Copilot-instructions.md

Example prompts

  • “/omh-agent-instructions”

What it can do on your machine

Read from SKILL.md and the folder at commit 7cd0d02. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • cursor

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Omh Agent Instructions loads about 2.2k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 101 tokens; SKILL.md has 1,075 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~101
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from rlaope/oh-my-hermes at commit 7cd0d02, republished under its MIT licence (© rlaope). 1,075 words, ~2,153 tokens.

Download SKILL.mdSave it as .claude/skills/omh-agent-instructions/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
omh-agent-instructions
description
[omh] Agent instruction file for a repo -- AGENTS.md, CLAUDE.md, a Cursor rule: write or update what an agent cannot derive from the code, inside a marked region, with every command verified or marked unverified and no counts that drift. Use when the user says: agent-instructions, agents.md, claude.md, gemini.md, copilot-instructions.md, .cursorrules, cursor rules, cursor rule.

Agent Instructions

This is a Hermes-native agent-instructions workflow skill.

Why This Exists

agent-instructions exists because the file every handoff target reads first had no owner: rules-distill extracts rule candidates, codebase-onboarding builds a human reading path, and context aligns terminology, and each reads that file without writing it.

First Steps

  • List every instruction file and which agent reads it before proposing a section.
  • Run or ask for the observed run of each command before marking it verified.

Do Not Use When

  • The ask is distilling repeated lessons into reviewed rule candidates; use rules-distill.
  • The ask is a reading path through the codebase for a new engineer; use codebase-onboarding.
  • The ask is project terminology alignment -- reviewing the terms this project uses and correcting inconsistent vocabulary; use context.
  • The ask is user-facing product documentation; use product-docs.

Examples

Good example:

  • Prompt: update our CLAUDE.md
  • Expected behavior: Inventory the instruction files, run or collect each build and test command, mark each verified or unverified, and replace only the marked region with the commands, the generated-file map, the gates, and the costed pitfalls, refusing any count or line number.
  • Why: An instruction file that states an unrun command or a stale count sends every later agent the wrong way.

Bad example:

  • Prompt: add that the suite has 4,100 tests and the router is at line 212 of chat.py
  • Expected behavior: Refuse both values, and write the command that counts the tests and the symbol that locates the router instead.
  • Why: Both numbers were already wrong by the next merge.

Completion Checklist

  • Every instruction file and its reader are listed.
  • Every command is marked verified with an observed run, or unverified.
  • Only the marked region changed, and hand-written text is byte-for-byte.
  • No count, line number, or value the code already states was written.
  • Every generated file names its source, its regenerate command, and its gate.

Recovery Notes

  • If a command cannot be run here, write it marked unverified with what would verify it.
  • If the file has no markers, insert them once around the new section and leave everything else untouched.

Workflow Lane

  • Current lane: Coding handoff (idea-to-deploy, llm-app-dev, cto-loop, deploy-and-monitor, code-review, build-failure-triage, verification-gate, security-safety-review, +28 more) - coding owners, handoffs, review, CI, and merge evidence.
  • If intent belongs to another lane, hand back to oh-my-hermes or name the adjacent workflow.
  • Shared product, routing, compatibility, and evidence rules: omh-routing/references/skill-common-rail.md.

Use When

Use when the repository's agent instruction file is being written or kept current: AGENTS.md, CLAUDE.md, GEMINI.md, a Cursor rule, or a Copilot instructions file. The output is the build and test commands each marked verified or unverified, the generated-file map with its regenerate command and gate, the byte-exact gates, and the pitfalls that cost time, written inside a marker-delimited region so hand-written sections survive.

Strong routing signals: `agent-instructions`, `agents.md`, `claude.md`, `gemini.md`, `copilot-instructions.md`, `.cursorrules`, `cursor rules`, `cursor rule`, `agent instruction file`, `agent instructions file`, `instructions file for agents`, `set up agents.md`, `update our claude.md`, `write an agents.md`

Catalog Metadata

Category: planning Phase: agent-instructions Hermes role: planner Quality tier: verified-command-and-region-gated Reasoning demand: standard

Quality bar:

  • Inventory every instruction file first and respect closest-file-wins nesting.
  • Load references/instruction-file-method.md for the section order, the marker convention, the verified and unverified command form, and the drift rules instead of recalling them.
  • Record each pitfall with what it cost, so a reader can tell a scar from a preference.
  • Pair every generated file with its source, its regenerate command, and the gate that checks it.
  • Keep prepared, verified, and written as separate states for every command and section.

Handoff policy:

Keep the section plan, the command verification record, and the region update in Hermes. Every command's outcome is recorded only from executor, operator, or wrapper observed output; the file is written by the executor, and only inside its marked region.

Required inputs:

  • which instruction files exist, where they sit, and which agents read them
  • the build, test, lint, and regenerate commands the repository uses
  • which files are generated, from what source, and which gate checks them
  • the pitfalls that have cost time, each with what it cost
  • observed output for every command written into the file
Show full SKILL.md (397 more words)Show less

Expected outputs:

  • instruction_file_inventory/v1
  • command_verification_record/v1
  • instruction_region_update/v1
  • drift_refusal_note/v1 when a requested line would record a count or a line number

Artifact expectations:

  • instruction_file_inventory/v1 lists every instruction file, its path, the agents that read it, and which one is closest to each directory, since the closest file wins
  • command_verification_record/v1 marks every command verified, with the observed exit status and when, or unverified, and nothing is written as verified without an observed run
  • instruction_region_update/v1 replaces only the text between <!-- omh:agent-instructions:begin --> and <!-- omh:agent-instructions:end -->, and inserts the markers once when absent, so every hand-written section outside them is left byte-for-byte
  • drift_refusal_note/v1 names each requested count, line number, or other value the code already states, and writes the command or the file that derives it instead

Safety rules:

  • Never write outside the marker-delimited region: the text before <!-- omh:agent-instructions:begin --> and after <!-- omh:agent-instructions:end --> is hand-written and stays byte-for-byte.
  • Never write a command as verified without an observed run; mark it unverified instead.
  • Refuse to record counts, line numbers, test totals, or file sizes; they drift, so point at the command or file that derives them.
  • Write only what an agent cannot derive from the code; restating the code is drift waiting to happen.
  • Never copy secrets, tokens, or private hostnames into an instruction file.

Runtime Evidence

Preferred harness for this skill: docs-specialist.

sh
omh runtime record --skill agent-instructions --harness docs-specialist --status started

Record observed delegation results; otherwise return not_available or not_observed. Prepared OMH routing is not execution, review, CI, merge-readiness, or merge evidence.

  • Treat wrapper memory/context summaries as advisory local context, not proof of opaque Hermes memory reads or changes. Preserve workflow intent and stop conditions; verify before claiming completion. Reply in the user's own words and the host's own voice: its SOUL.md persona owns reply language, tone, speech level, and sentence endings, progress updates included (where it sets no language, use the one the user wrote in), and OMH shapes structure and content only; OMH's record terms (surface, lane, wrapper, handoff, evidence boundary, not_observed) stay in records and tool calls, never in the sentence the user reads unless they ask about one; and when a stop condition or a decision the user owns ends the turn, offer the next action as a question rather than declaring what will not be done.

Use Hermes-native subagent/delegation features when available: native subagents -> Hermes delegation when available, otherwise sequential lanes.

Shared product, compatibility, topology, memory, harness, and execution rules: omh-routing/references/skill-common-rail.md. Load it when applicable; otherwise name an unavailable capability.

© rlaope, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/omh-agent-instructions of rlaope/oh-my-hermes.

  • SKILL.md
  • references/instruction-file-method.md

Open the folder on GitHubat commit 7cd0d02

Compare with similar skills

Omh Agent Instructions next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Omh Agent Instructions compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Omh Agent Instructions this skillrlaope/oh-my-hermes3.2k—~2.2kAutomated safety check: PassMIT
Using Agent Skillsaddyosmani/agent-skills104k4 repos~2.4kAutomated safety check: PassMIT
Claude ReflectBayramAnnakov/claude-reflect1.8k2 repos~627Automated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Writing For Agentsbestofjs/bestofjs3.1k18 repos~2.7kAutomated safety check: PassMIT
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~11kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    104k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed
  • Claude Reflect

    BayramAnnakov/claude-reflect

    Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.

    1.8k GitHub starsUsed in 2 repos~627 tokens
    Agent WorkflowsAuto-check passed
  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 9 days ago
    Agent WorkflowsAuto-check passed
  • Writing For Agents

    bestofjs/bestofjs

    Writing documents for agents. An agent skill from bestofjs/bestofjs.

    3.1k GitHub starsUsed in 18 repos~2.7k tokens
    Agent WorkflowsAuto-check passed
  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~11k tokens
    Agent WorkflowsAuto-check passed
  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated 4 days ago
    Agent WorkflowsAuto-check passed

More from rlaope/oh-my-hermes

All 143 skills in this repo
  • Omh Accessibility Audit

    rlaope/oh-my-hermes

    [omh] Screen-reader or keyboard accessibility gaps: prepare WCAG, keyboard, focus, screen-reader, target-size, and reflow evidence gates for UI surfaces.

    3.2k GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Omh Agent Evaluation

    rlaope/oh-my-hermes

    [omh] Choosing between coding agents on evidence: compare executor or agent choices on reproducible tasks using quality, cost, time, tool, and evidence metrics.

    3.2k GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Omh Agent Ops Review

    rlaope/oh-my-hermes

    [omh] AI agent progress for managers: help managers inspect AI-agent progress, blockers, quality gates, and throughput levers.

    3.2k GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Omh AI Slop Cleaner

    rlaope/oh-my-hermes

    [omh] Messy or AI-generated code to clean up: delete AI-generated slop, dead code, and duplication while observable behavior stays identical.

    3.2k GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Omh App Debugging

    rlaope/oh-my-hermes

    [omh] Application code misbehaves -- a wrong value, a flaky test, a lost update: reproduce it first, form competing hypotheses, discriminate them with the cheapest observation, and only then fix the…

    3.2k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Omh Apple Design

    rlaope/oh-my-hermes

    [omh] Designing or reviewing an iOS, macOS, or Apple-style UI: prepare native Apple UI or Apple marketing product-visual direction, review, and improvement briefs with evidence-backed remediation…

    3.2k GitHub stars~2.3k tokensUpdated today
    Auto-check passed

Categories

Questions about Omh Agent Instructions

What does Omh Agent Instructions do?

[omh] Agent instruction file for a repo -- AGENTS.md, CLAUDE.md, a Cursor rule: write or update what an agent cannot derive from the code, inside a marked region, with every command verified or…. Omh Agent Instructions is an agent skill from rlaope/oh-my-hermes.md, a Cursor rule: write or update what an agent cannot derive from the code, inside a marked region, with every command verified or marked unverified and no counts that drift.

When should I use Omh Agent Instructions?

Omh Agent Instructions fits situations like: the user says: agent-instructions; copilot-instructions.md.

How do I install Omh Agent Instructions in Claude Code?

Run `npx skills add rlaope/oh-my-hermes --skill omh-agent-instructions -a claude-code`. Or copy the skill folder (skills/omh-agent-instructions in rlaope/oh-my-hermes) into .claude/skills/omh-agent-instructions in your project. Claude Code loads it when a task matches its description.

How do I install Omh Agent Instructions in Codex?

Run `npx skills add rlaope/oh-my-hermes --skill omh-agent-instructions -a codex`. Or copy the skill folder (skills/omh-agent-instructions in rlaope/oh-my-hermes) into .agents/skills/omh-agent-instructions in your project. Codex loads it when a task matches its description.

Can I use Omh Agent Instructions in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rlaope/oh-my-hermes --skill omh-agent-instructions -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/omh-agent-instructions, .gemini/skills/omh-agent-instructions, .github/skills/omh-agent-instructions and .opencode/skills/omh-agent-instructions in your project.

What does Omh Agent Instructions need to run?

Going by SKILL.md and its folder, Omh Agent Instructions needs the command-line tools its instructions call (cursor).

Does Omh Agent Instructions access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Omh Agent Instructions safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Omh Agent Instructions use?

Omh Agent Instructions is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Omh Agent Instructions use?

About 2.2k tokens (SKILL.md is roughly 8.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 654 tokens, read only when the agent opens those files.

What are the alternatives to Omh Agent Instructions?

Skills that share tags, products or a category with Omh Agent Instructions: Using Agent Skills (addyosmani/agent-skills, 104k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.8k stars), Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars) and Writing For Agents (bestofjs/bestofjs, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Omh Agent Instructions?

rlaope (a GitHub user) maintains it in rlaope/oh-my-hermes, which has 3,243 GitHub stars. The repository holds 143 skills in this directory. The repository was last updated on October 10, 2026.

Source: rlaope/oh-my-hermes on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.