repo-native-alignment: Skill for Claude Code

.agents/skills/teach-oh/SKILL.md

teach-oh is a skill for Claude Code, Codex from open-horizon-labs/repo-native-alignment. It costs 33 tokens per session (4,105 once invoked), scanned A, original, MIT.

A project-setup skill that explores a codebase, asks about its goals, and saves shared context in AGENTS.md.

In plain words
What is it for?
It is for starting work on a new project, onboarding an AI coding tool, recording project strategy, and optionally using Repo-Native Alignment for code exploration.
Why use it?
It gives coding agents a durable explanation of the project, reducing repeated onboarding and misunderstandings when aims or tools change.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is open-horizon-labs/repo-native-alignment's own configuration. It tells Claude Code and Codex how to work on repo-native-alignment itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything repo-native-alignment configures →

Reuse

Borrowing it

Nothing to install: this file belongs to open-horizon-labs/repo-native-alignment. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/open-horizon-labs/repo-native-alignment/main/.agents/skills/teach-oh/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/open-horizon-labs/repo-native-alignment

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for teach-oh

README.md
[![agentmods](https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/teach-oh/github.svg)](https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/teach-oh)
Your own site
<a href="https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/teach-oh"><img src="https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/teach-oh/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.

agentmods 80×15 button for teach-oh

Your own site · 80×15
<a href="https://agentmods.dev/skills/open-horizon-labs/repo-native-alignment/teach-oh"><img src="https://agentmods.dev/badge/skills/open-horizon-labs/repo-native-alignment/teach-oh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,105 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.04105
Opus 5 $0.00016 $0.02053
Sonnet 5 $0.00007 $0.00821
Haiku 4.5 $0.00003 $0.00411

Measured 11d ago against content hash 8a383e7346aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

teach-oh 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.

.agents/skills/teach-oh/SKILL.md · 508 lines

How it starts

The opening of the file, as written. The whole thing — 508 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/teach-oh

Setup that gathers project context and saves it to AGENTS.md (the cross-agent standard). Run when starting on a project or when strategy/aims have shifted.

When to Use

Invoke /teach-oh when:

  • Starting on a new project - Before diving into work
  • Context keeps getting lost - AI assistants don't "get" your project
  • Onboarding a new AI tool - Establish shared understanding upfront
  • After major strategic shifts - When aims or constraints have changed

Do not use when: You're mid-task. This is setup, not execution.

The Process

Step 0: Check for RNA MCP (Repo-Native Alignment)

Before exploring, check if RNA is available — it makes everything that follows richer.

Detection (in order):

  1. Check if RNA's search, repo_map, list_roots, or outcome_progress tools are available in the current session
  2. Check if repo-native-alignment is on PATH: which repo-native-alignment
  3. Check if .mcp.json references repo-native-alignment or rna-server

If RNA is available: Proceed to Step 1. Use repo_map for orientation and search for symbols, artifacts, neighbors, and impact instead of Grep/Read.

If RNA is NOT available: Offer to install it:

"I can set up Repo-Native Alignment (RNA) — it gives me semantic code search, graph traversal, and business context awareness across your codebase. Takes ~1 minute. Want me to install it?"

If accepted:

  1. Detect platform and chip:

    OS=$(uname -s)
    ARCH=$(uname -m)
    CHIP=$(sysctl -n machdep.cpu.brand_string 2>/dev/null || echo "")
    
    • macOS ARM M4+: Darwin + arm64 + brand_string contains "M4" → use darwin-arm64-m4
    • macOS ARM (other): Darwin + arm64 → use darwin-arm64
    • Linux x86_64: Linux + x86_64 → use linux-x86_64
  2. Invoke the repo-local /rna-mcp:setup skill. It owns installation, selects a successful CI release artifact for an immutable commit, verifies the artifact, and configures the client. Never download a mutable latest artifact or use a locally compiled binary as a shipped build.

Read the full file on GitHub · 508 lines

Changes

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.

  1. 11d ago First seen · 508 lines · 33 tokens per session scan A 8a383e7346aa

Subscribe to this mod's changes

teach-oh is a skill published in the GitHub repository open-horizon-labs/repo-native-alignment (5 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 4,105 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens