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 agentmods add instructions/jandedobbeleer/oh-my-posh/agents-mdgit clone --depth 1 https://github.com/JanDeDobbeleer/oh-my-poshWhat 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 | $0.01987 | $0.01987 |
| Opus 5 | $0.00993 | $0.00993 |
| Sonnet 5 | $0.00397 | $0.00397 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
oh-my-posh AGENTS.md 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 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.
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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
General coding guidelines, commit conventions, and agent workflows for this repository.
Project Overview
Oh My Posh is a cross-shell prompt theme engine written in Go. It renders prompt segments by
querying an Environment abstraction that wraps all OS/shell interactions.
Tech Stack
| Layer | Technology |
|---|---|
| Core engine | Go (module root: src/) |
| Documentation site | Docusaurus (MDX) - website/ |
| Themes | JSON - themes/ |
| Config format | TOML / JSON / YAML |
| Package/installer scripts | packages/ |
| Build scripts | build/ |
Key Commands
# Go - run from src/
go test ./...
go test ./segments/... -run TestFoo # single test
golangci-lint run
# Docs - run from website/
npm run start # local dev server
npm run build # validate before opening a docs PR
Codebase Exploration
Always explore the actual codebase before planning or writing code. Do not rely on memory or assumptions. Use the file system tools to read relevant files first - the codebase evolves and the feature you're asked to add may already exist.
Repository Layout
src/
segments/ # One Go file + one _test.go per segment
prompt/ # Core rendering engine
runtime/ # OS/shell abstraction layer
themes/ # Bundled JSON theme files
website/ # Docusaurus docs site (MDX pages, sidebar config, JSON schema)
packages/ # Installer/package manifests
build/ # CI build helpers
Key paths inside src/:
| Path | Purpose |
|---|---|
src/segments/ |
One .go + one _test.go per segment |
src/config/segment_types.go |
Segment type registry (gob + string constants) |
src/cli/ |
CLI commands (cmdtree); root.go is the entry point |
src/prompt/engine.go |
Segment rendering loop |
src/cache/ |
Existing TTL/file/command-path cache infrastructure |
src/runtime/ |
Environment abstraction + mock |
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 First seen · 188 lines · 1,987 tokens per session scan A adac1bbddb43
oh-my-posh AGENTS.md is an instructions file published in the GitHub repository JanDeDobbeleer/oh-my-posh (23,372 stars, last pushed yesterday), licensed MIT. It adds 1,987 tokens to every session, about $0.0099 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 instructions, from other repositories
awesome-go AGENTS.md
Instructions for avelino/awesome-go, covering awesome-go · llm contribution guide, project snapshot, when modifying the awesome list, coding guidelines and testing & validation.
thunderid AGENTS.md
Instructions for thunder-id/thunderid, covering project overview, where to look next, search hygiene, validation ladder and product name rules.
thunderid copilot-instructions.md
Instructions for thunder-id/thunderid: All project coding standards, conventions, and guidelines are defined in AGENTS.md.
PromptHub AGENTS.md
AGENTS.md instructions for legeling/PromptHub, covering prompthub — project context & development rules, 0. agent operating contract, 0.1 source-of-truth lookup order, 0.2 mandatory change gate and 0.3 existing-feature modification rule.
awesome-go copilot-instructions.md
Instructions for avelino/awesome-go, a project described as: A curated list of awesome Go frameworks, libraries and software.
faker CLAUDE.md
Claude Code instructions for jaswdr/faker, covering claude.md, repository overview, core architecture, common commands and testing.