Borrowing it
Nothing to install: this file belongs to EZotoff/ez-omo-config. 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/EZotoff/ez-omo-config/master/AGENTS.mdgit clone --depth 1 https://github.com/EZotoff/ez-omo-configWrote 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/ezotoff/ez-omo-config/agents-md)<a href="https://agentmods.dev/instructions/ezotoff/ez-omo-config/agents-md"><img src="https://agentmods.dev/badge/instructions/ezotoff/ez-omo-config/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/ezotoff/ez-omo-config/agents-md"><img src="https://agentmods.dev/badge/instructions/ezotoff/ez-omo-config/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 | $0.07983 | $0.07983 |
| Opus 5.5 | $0.03193 | $0.03193 |
| Sonnet 5.5 | $0.01597 | $0.01597 |
| Haiku 4.5 | $0.00798 | $0.00798 |
Grade B, and why
ez-omo-config 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 18d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
**Prerequisite**: `sudo apt install -y inotify-tools` for the watcher service. Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
5. Structural fixes are mandatory for new bash/python tooling: `set -euo pipefail` for bash, `subprocess.run([...])` list-form for Python, no string interpolation into Python source. How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ez-omo-config — Agent Instructions
What This Is
This project is the versioned config store for OpenCode and Oh-My-OpenAgent (OMO). The active configs are symlinked to this repo — editing a file here IS editing the live config.
Config Locations
| Purpose | Store path (git-tracked) | Live symlink (OpenCode reads this) |
|---|---|---|
| OpenCode config | configs/opencode/opencode.json |
~/.config/opencode/opencode.json → store |
| OMO config | configs/oh-my-openagent/oh-my-openagent.json |
~/.config/opencode/oh-my-openagent.json → store |
| Provider retry plugin | configs/opencode/provider-connect-retry.mjs |
~/.config/opencode/provider-connect-retry.mjs → store |
| Retry error registry | configs/retry-errors.json |
~/.config/opencode/retry-errors.json → store |
| Agent default guard | configs/opencode/agent-default-guard.mjs |
~/.config/opencode/agent-default-guard.mjs → store |
| Auth / API keys | — | ~/.local/share/opencode/auth.json (NEVER committed) |
How It Works
Live configs are symlinks pointing into this repo:
~/.config/opencode/opencode.json → ~/ez-omo-config/configs/opencode/opencode.json
~/.config/opencode/oh-my-openagent.json → ~/ez-omo-config/configs/oh-my-openagent/oh-my-openagent.json
There is ONE file, not two. Editing either path modifies the same file. Changes are immediately visible to OpenCode AND tracked by git.
Rules for Agents
- Edit the store path (files in this repo). The symlinks ensure OpenCode sees the change.
- No propagation needed. The old copy-and-adapt workflow is dead. There is no second file to sync.
- Never commit auth/API keys.
~/.local/share/opencode/auth.jsonis machine-local. - No machine-specific paths.
opencode.jsonuses relative paths for all local plugins (e.g../provider-connect-retry.mjs,../../.opencode/plugin/clickable-links.ts), resolved by OpenCode against the config file's directory. No manual path updates are needed on a new machine. - Validate JSON after editing. Run
python3 -c "import json; json.load(open('path'))"on changed files. - Server vs TUI restart. Closing/reopening the TUI does NOT restart the
opencode serveserver process. Plugins, OMO runtime, and in-memory session state are initialized once at server startup. Config changes (plugin array, agent settings) require a server restart to take full effect (the formeromo-tg.serviceunit is masked/retired). Never bare-restart — running sessions lose their in-flight turns; usescripts/restart-with-continuation.sh(see "Session-safe OpenCode server restarts" in the global AGENTS.md) so active sessions are snapshotted and auto-continued. Always verify withps -eo pid,lstart,etime,args | grep 'opencode serve'that the server start time actually changed before assuming a restart worked.
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.
- 18d ago Changed · +10 lines · +517 tokens per session 1abf5ae23387
- 19d ago Changed · +21 lines · +731 tokens per session 651c589a081a
- 25d ago Changed · -27 tokens per session a1a651f096d7
- 1mo ago Changed · +3 lines · +155 tokens per session 32b9402f9f54
- 1mo ago Changed · +13 lines · +528 tokens per session 79d722f948a4
- 1mo ago Changed · +21 lines · +426 tokens per session 1889f98181b4
- 1mo ago Changed · +1 lines · +37 tokens per session a7d85e5ca183
- 1mo ago Changed · +83 tokens per session 31287d661c8f
- 1mo ago Changed · +15 lines · +1,123 tokens per session d7e7da9fc9f0
- 1mo ago First seen · 218 lines · 4,410 tokens per session scan B 64346bb4cae2
ez-omo-config AGENTS.md is an instructions file published in the GitHub repository EZotoff/ez-omo-config (6 stars, last pushed 7d ago), licensed MIT. It adds 7,983 tokens to every session, about $0.0319 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
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.
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).